Intro to Deep Learning for Computer Vision

Size: px
Start display at page:

Download "Intro to Deep Learning for Computer Vision"

Transcription

1 High Level Computer Vision Intro to Deep Learning for Computer Vision Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de

2 Overview Today Recent successes of Deep Learning necessarily incomplete and biased :-) What is Deep Learning? Neural network basics Supervised learning with error backpropagation [reading Bishop chapter ] Convolutional Neural Networks "2

3 Computer Vision: Image Classification 1000 classes; 1ms for an image; 92.5% recognition rate "3

4 Architectures get deeper Top 5 error More accurate caffe-alex vgg-f vgg-m googlenet-dag vgg-verydeep-16 resnet-50-dag resnet-101-dag resnet-152-dag caffe-alex vgg-f vgg-m googlenet-dag vgg-verydeep-16 resnet-50-dag resnet-101-dag resnet-152-dag ~ 2.6x improvement in 3 years "4

5 Architectures get deeper "5

6 Architectures get deeper "6

7 Computer Vision: Semantic Segmentation Badrinarayanan et al SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling "7

8 Computer Vision: Semantic Segmentation Input Groundtruth Output Yang He; Wei-Chen Chiu; Margret Keuper; Mario Fritz STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 "8

9 Deep(er)Cut: Joint Subset Partition & Labeling for Multi Person Pose Estimation DeepCut: Joint Subset Partition and Labeling for Multi-Person Pose Estimation L. Pishchulin, E. Insafutdinov, S. Tang, B. Andres, M. Andriluka, P. Gehler, and B. Schiele, CVPR 16 DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model E. Insafutdinov, L. Pishchulin, B. Andres, M. Andriluka, and B. Schiele, ECCV 16

10 Analysis - overall performance Best Methods now: deep learning takes over PCKh total, MPII Single Person Best Method as of ICCV 13 since CVPR 14, dataset has become de-facto standard benchmark large training set facilitated development of deep learning methods Progress in Person Detection and Human Pose Estimation in the last Decade Bernt Schiele "10

11 Predicting the Future Apratim Bhattacharyya; Mateusz Malinowski; Bernt Schiele; Mario Fritz Long-Term Image Boundary Extrapolation arxiv: [cs.cv] & AAAI 18 "11

12 Computer Vision & NLP: Image Captioning Ours: a person on skis jumping over a ramp Ours: a skier is making a turn on a course Ours: a cross country skier makes his way through the snow Ours: a skier is headed down a steep slope Baseline: a man riding skis down a snow covered slope Rakshith Shetty; Marcus Rohrbach; Lisa Anne Hendricks; Mario Fritz; Bernt Schiele Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training arxiv: [cs.cv], ICCV 2017 "12

13 Computer Vision + NLP: Visual Turing Test What is on the refrigerator? What is the colour of the comforter? What is the color of the comforter? How many drawers are there? magnet, paper blue, white 3 Mateusz Malinowski; Mario Fritz A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input Neural Information Processing Systems (NIPS), Mateusz Malinowski; Marcus Rohrbach; Mario Fritz Ask Your Neurons: A Neural-based Approach to Answering Questions about Images IEEE International Conference on Computer Vision (ICCV), 2015, "13

14 AI and Planning "14

15 Robotics "15

16 Creative Aspects deepart.io "16

17 Imitating famous painters UVA DEEP LEARNING COURSE EFSTRATIOS GAVVES DEEPER INTO DEEP LEARNING AND OPTIMIZATIONS 19-19

18 Privacy & Safety Seong Joon Oh; Mario Fritz; Bernt Schiele Adversarial Image Perturbation for Privacy Protection - A Game Theory Perspective arxiv: [cs.cv], ICCV Tribhuvanesh Orekondy; Bernt Schiele; Mario Fritz Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images arxiv: [cs.cv], ICCV "18

19 Overview Today Recent successes of Deep Learning necessarily incomplete What is Deep Learning? Neural network basics Supervised learning with error backpropagation [reading Bishop chapter ] Convolutional Neural Networks "19

20 Deep Learning Deep Learning is based on Availability of large datasets Massive parallel compute power Advances in machine learning over the years Strong improvements due to Internet (availability of large-scale data) GPUs (availability of parallel compute power) Deep / hierarchical models with end-to-end learning "20

21 Overview of Deep Learning "21

22 x<latexit sha1_base64="f2 y<latexit sha1_base64="l2 Traditional Approach feature extraction (hand crafted) Classification Car Feature extraction often hand crafted and fixed might be too general (not task-specific enough) might be too specific (does not generalize to other tasks) How to achieve best classification performance more complex classifier (e.g. multi-feature, non-linear)? how specialized for the task? "22

23 Features Alone Can Explain (Almost) 10 Years of Progress workshop 14] Progress in Person Detection and Human Pose Estimation in the last Decade Bernt Schiele "23

24 Motivation Features are key to recent progress in recognition Multitude of hand-designed features currently in use SIFT, HOG, LBP, MSER, Color-SIFT. Where next? Better classifiers? Or keep building more features? Felzenszwalb, Girshick, McAllester and Ramanan, PAMI 2007 Yan & Huang (Winner of PASCAL 2010 classification competition) slide credit: Rob Fergus

25 Hand-Crafted Features LP-β Multiple Kernel Learning (MKL) Gehler and Nowozin, On Feature Combination for Multiclass Object Classification, ICCV different kernels PHOG, SIFT, V1S+, Region Cov. Etc. MKL only gets few % gain over averaging features à Features are doing the work slide credit: Rob Fergus

26 x<latexit sha1_base64="f2 <latexit sha1_base64="qg0sjzvwmzsqdenusdi4/2+vvru=">aaacknicbvdlsgmxfm34rpvvdekmwiqkpcz0ge1cqlhxwce+ob1kjr3thmyejbmhdp0en/6kmy6u4typmx2jwg8edufck9wcj+rmktocghubw9s7u4m95p7b4dfx6us0iyniukjtgaei5rajnplqv0xxaiuciodwadrdu5nffaihwea/qleitkf6pnmzjupl3drt3jlf0hz9x47nxkvuyhclwu3khxzfzfo5c44xhueb7gzcicosilo4e3jqj1fjbiq9iufvdk9i3ysnlqh1u5nol6crb y<latexit sha1_base64="l2 Deep Learning: Trainable features Features features = g(x, ) Classifier y = f(features,!) Car Parameterized feature extraction Features should be efficient to compute efficient to train (differentiable) "26

27 x<latexit sha1_base64="f2 <latexit sha1_base64="qg0sjzvwmzsqdenusdi4/2+vvru=">aaacknicbvdlsgmxfm34rpvvdekmwiqkpcz0ge1cqlhxwce+ob1kjr3thmyejbmhdp0en/6kmy6u4typmx2jwg8edufck9wcj+rmktocghubw9s7u4m95p7b4dfx6us0iyniukjtgaei5rajnplqv0xxaiuciodwadrdu5nffaihwea/qleitkf6pnmzjupl3drt3jlf0hz9x47nxkvuyhclwu3khxzfzfo5c44xhueb7gzcicosilo4e3jqj1fjbiq9iufvdk9i3ysnlqh1u5nol6crb y<latexit sha1_base64="l2 Deep Learning: Joint Training of all Parameters Features features = g(x, ) Classifier y = f(features,!) Car Parameterized feature extraction Features should be efficient to compute End-to-End System efficient to train (differentiable) Joint training of feature extraction and classification Feature extraction and classification merge into one pipeline "27

28 x<latexit sha1_base64="f2 <latexit sha1_base64="qg0sjzvwmzsqdenusdi4/2+vvru=">aaacknicbvdlsgmxfm34rpvvdekmwiqkpcz0ge1cqlhxwce+ob1kjr3thmyejbmhdp0en/6kmy6u4typmx2jwg8edufck9wcj+rmktocghubw9s7u4m95p7b4dfx6us0iyniukjtgaei5rajnplqv0xxaiuciodwadrdu5nffaihwea/qleitkf6pnmzjupl3drt3jlf0hz9x47nxkvuyhclwu3khxzfzfo5c44xhueb7gzcicosilo4e3jqj1fjbiq9iufvdk9i3ysnlqh1u5nol6crb y<latexit sha1_base64="l2 Deep Learning: Joint Training of all Parameters Features features = g(x, ) Classifier y = f(features,!) Car End-to-End System All parts are adaptive No differentiation between feature extraction and classification Non linear transformation from input to desired output "28

29 x<latexit sha1_base64="f2 <latexit sha1_base64="qg0sjzvwmzsqdenusdi4/2+vvru=">aaacknicbvdlsgmxfm34rpvvdekmwiqkpcz0ge1cqlhxwce+ob1kjr3thmyejbmhdp0en/6kmy6u4typmx2jwg8edufck9wcj+rmktocghubw9s7u4m95p7b4dfx6us0iyniukjtgaei5rajnplqv0xxaiuciodwadrdu5nffaihwea/qleitkf6pnmzjupl3drt3jlf0hz9x47nxkvuyhclwu3khxzfzfo5c44xhueb7gzcicosilo4e3jqj1fjbiq9iufvdk9i3ysnlqh1u5nol6crb y<latexit sha1_base64="l2 Deep Learning: Complex Functions by Composition Features features = g(x, ) Classifier y = f(features,!) Car End-to-End System How can we build such systems? What is the parameterization (hypothesis)? Composition of simple building blocks can lead to complex systems (e.g. neurons - brain) "29

30 x<latexit sha1_base64="f2 y<latexit sha1_base64="l2 Deep Learning: Complex Functions by Composition Car How can we build such systems? What is the parameterization (hypothesis)? Composition of simple building blocks can lead to complex systems (e.g. neurons - brain) each block has trainable parameters Each block has trainable parameters i "30

31 x<latexit sha1_base64="f2 y<latexit sha1_base64="l2 Deep Learning: Complex Functions by Composition Car intermediate representations How can we build such systems? What is the parameterization (hypothesis)? Composition of simple building blocks can lead to complex systems (e.g. neurons - brain) each block has trainable parameters Each block has trainable parameters i "31

32 x<latexit sha1_base64="f2 y<latexit sha1_base64="l2 Deep Learning: Complex Functions by Composition Car Lee et al. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations "32

33 x<latexit sha1_base64="f2 y<latexit sha1_base64="l2 Deep Learning: Complex Functions by Composition Car Lee et al. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations "33

34 x<latexit sha1_base64="f2 y<latexit sha1_base64="l2 Deep Learning: Complex Functions by Composition Car Lee et al. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations "34

35 Summary of Main Ideas in Deep Learning 1. Learning of feature extraction (across many layers) 2. Efficient and trainable systems by differentiable building blocks 3. Composition of deep architectures via non-linear modules 4. End-to-End training: no differentiation between feature extraction and classification "35

36 Summary of Main Ideas in Deep Learning 1. Learning of feature extraction (across many layers) 2. Efficient and trainable systems by differentiable building blocks 3. Composition of deep architectures via non-linear modules 4. End-to-End training: no differentiation between feature extraction and classification "36

37 Overview Today Recent successes of Deep Learning necessarily incomplete What is Deep Learning? Neural network basics Supervised learning with error backpropagation [reading Bishop chapter ] Convolutional Neural Networks "37

38 Some Inspiration from the (Human) Brain Motivation from the brain effective universal learning machine? Highly simplified neural model Combination of inputs is linear No spike No temporal model Fixed topology Properties we want: differentiable efficient "38

39 <latexit sha1_base64="bt0wvb2/c4ych9uvc+nkbx5n5uq=">aaab+hicbvdlssnafl2pr1ofjbp0m1gef6ukiuhkcrpwwce+oa1hmp20qyetmdor1tavcencebd+ijv/xmmbhbyegdiccw/3zgkszpr2ng+rsla+sblv3c7t <latexit sha1_base64="ip0vb2yartlwduubaa6y x<latexit sha1_base64=" <latexit sha1_base64="t9knuvgwh0bdbnc+u4o54setwds=">aaab8hicbvbnswmxej31s9avqkcvwslus9kvqrgughepfeyhtevjptk2nmkusvzyl/4klx4u8erp8ea/mw33ok0pbh7vztazl4g z<latexit sha1_base6 <latexit sha1_base64= [Reading - Chapter Bishop 2006] Neural Network Basics Core component of a neural network: processing unit ~ neuron of the human brain a processing unit maps multiple input values onto one output value y<latexit sha1_base64= x 0,...,x D are input units w 0 is an external input called bias the propagation rule maps all input values on the actual input the activation function is applied to obtain: y := f(z) slide adapted from David Stutz "39

40 <latexit sha1_base64="8zyp5zxohwzp73ybmhg8do61faa="> <latexit sha1_base64="yvg82ih+xozcgc0czea6whqqg98=">aaacihicbvbns8naen34wetx1aoxwsj4kcurqfegqi8ek9gqnkvstpt2cbmjuxm1hp4ul/4vlx4u0zv+grc1b7u+ghi8n7m784jecoou++hmzm7nlyywlsrlk6tr65wnzbaju814i8uy1lcbnvwkxvsoupkrrhmabzjfbtensx95w7ursbralohdia6ucawjakve5vacq9yt4edbfjcd3aocaozakkkbl3mifu7v/h6mpgyn8luydnef9spvt+5oanpek0ivfgj2ku/2dzzgxcgt1jio5ybyzalgwsqflf3u8isyazrghusvjbjp5pmdr7brlt6esbalecbqz4mcrszkuwa7i4pd89cbi/9 <latexit sha1_base64="cgd6hc9y5yxoqh7kwfta8eyimfu=">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</latexit> i<latexit sha <latexit sha1_base64="z0ragrrbgeijgv <latexit sha1_base64="wtmrxvv1afs/uirgycbzxwafe4i=">aaacd3icbvdlssnafj3uv62vqes3g0urhjkiojtkqrcuk9ghtdfmppn22pkkzezugvihbvwvny4ucevwnx/jtm1cww9cohpovcy9x4sylcqyvo3c3pzc4lj+ubcyura+yw5u1wuyc0xqogshahpiekydulnumdkmbehcy6thdc5hfuowcend4foni+jw1a2otzfswnln/qexwjjsy5i7sb9spzcx8m5na <latexit sha1_base64="mtycvzzyxl <latexit sha1_base64="6eznfk1ek25sns <latexit sha1_base64="sh7gpcp8wxkv12c <latexit sha1_base64="eyrjlu/z1pz/6xn7koj <latexit sha1_base64="hp+6lruf2d3tzaldqaqqvekmxyw=" sha1_base64="c9rktwtrme5pezcp4bi4eewdoc4=" sha1_base64="vwmiait3qcyv3r6mnx5qxr1z2fa=" sha1_base64="hbtzlwl23bixrhv7kydwsfqoagk=" Neural Network Basics: Perceptron [Rosenblatt 1958] A single-layer perceptron consists of D input units and C output units input unit j : x j with j 2 {0,...,D}(x 0 := 1) propagation rule: weighted sum over inputs with weights value and additional bias w i0 DX z i = w ij x j + w i0 activation function: next slide output unit calculates output for class j=1 i : y i with i 2 {1,...,C} x j w 10 w C0 w ij w 1D w CD 0 1 DX y i (x, w) =f(z i )=f@ w ij x j + w i0 A = f j=1 0 1 w ij x j A j=0 slide adapted from David Stutz "40

41 Short Intro: Perceptron - Activation Functions slide taken from David Stutz "41

42 Single Layer Perceptron slide taken from David Stutz "42

43 Two-Layer Perceptron slide taken from David Stutz "43

44 l<latexit sh <latexit sha1_base64="biagji/gfszf20aqsz965gp/1ko=">aaab7nicbvbnsw i<latexit sha <latexit sha1_base64="m3py6/pva2qknlnzgofyvjzy5v4=">aaab8nicbvbnswmxej2tx7v+vt16crahxsquchprcnrwwmf+whyt2ttbhmatjckkzenp8ojbea/+gm/+g9n2d9r6yodx3gwz88kem21c99s l<latexit <latexit sha1_base64="5sfe1kkt6rzsezt3bso2rwcrf90=">aaacnxicbvdlssnafj34rpvvdelmsajtwpkiobtfcopcrqwrqlpdzdppp51jwsynekj+yo3/4uoxlhrx6y84rrf8hrg4nhmud+7xy8e12pajnte5nt0zw5orzy8sli1xvlbpdzqoylo0epg69ilmgoesbrweu4wvi9ix7mifho38i2umni/cm0hj1pgkf/kauwjg8ionqcevspqo53gfb9gvliaadnuivwywb+dxmrzzw049z/gnl/fbxsrtb/dlyffxxh/qxqvqn+wx8f/ifkskcjs9yr3bjwgiwqhuek3bjh1djymkobusl7ujzjghq9jjbundi <latexit sha1_base64="drjec8awsn+nsha0nudnp6wvlra=">aaacgnicbvdlsgnbejynrxhfqx69dayhgorderqpeoghj1hma7ixze4myzdznwwm1xcwficxf8wlb0w8irf/xsnjebmlgoqqbrq7/ehwdy7zy6wwlldw19lrmy3nre0de3evomwskcttkasq+uqzwunwbg6c1slfsoalvvv7xzfffwrkcxnewybijyb0qt7mlicrmry7yhm0jegkf3yjvyba1/etu+hdnfyu73sbkcx7s <latexit sha1_base64="lftn0prylzmqf6zriwchflmjqja=">aaab9hicbvbnswmxej2tx7v+vt16crahiprdefsifhrx4kgc/yb2ldk0buot7jpkc2xp7/diqrgv/hhv/hvtdg/a+mdg8d4mm/ocidntxpfbyaysrq1vzddzw9s7u3v5/yo6dmnfai2epftnagvkma <latexit sha1_base64="gobhlay4gk0oz6a8weqv0zxcycq=">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</latexit> Multi-Layer Perceptron (MLP) add additional L > 0 hidden layers in between the input and output layers m (l) m (0) = D m (L+1) = C layer has units with and then the output of unit in layer is given by: y (l) i = f m (l 1) X j=0 w (l) ij y(l 1) j 1 A a multi-layer perceptron models a function: y(,w):r D! R C y(x, w) = 0 1 y 1 (x, w) y C (x, w) C A = (x, w) C. A C (x, w) y (L+1) y (L+1) slide adapted from David Stutz "44

45 x<latexit sha1_base64="f2yzimwbr/dgjz y<latexit sha1_base64="l29wxoub9d Training: Overview Car? Setting generate output y for input x (forward pass) "45

46 x<latexit sha1_base64="f2yzimwbr/dgjz y<latexit sha1_base64="l29wxoub9d Training: Overview Error? Setting generate output y for input x (forward pass) when there is an error, propagate error backwards to update weights (error back propagation)

47 Network Training slide taken from David Stutz "47

48 <latexit sha1_base64="lbhufbfzeo+wstvcxlb/mie6vhq=">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</latexit> <latexit sha1_base64="7kynmkdp7c6elhiyibpi+qyvzcu=">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</latexit> Network Training - Error Measures Sum-of-squared error function: E(w) = NX E n (w) = 1 2 n=1 weight vector NX n=1 CX (y i (x n,w) t ni ) 2 i=1 i-th component of function y i-th entry of target t Cross-entropy error function NX NX CX E(w) = E n (w) = t ni log y i (x n,w) n=1 n=1 i=1 slide adapted from David Stutz "48

49 <latexit sha1_base64="mselxol8+csqoz9dzmua0i0z984=">aaab7hicbvbns8naej34wetx1aoxxslus0 <latexit sha1_base64="lbhufbfzeo+wstvcxlb/mie6vhq=">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</latexit> w<latexit sha1_base64="gme7o Learning by Optimization Highly non-convex error landscape E(w) E(w) = NX E n (w) = 1 2 n=1 NX n=1 CX (y i (x n,w) t ni ) 2 i=1 "49

50 <latexit sha1_base64="mselxol8+csqoz9dzmua0i0z984=">aaab7hicbvbns8naej34wetx1aoxxslus0 w<latexit sha1_base64="gme7o Learning by Optimization E(w) "50

51 <latexit sha1_base64="mselxol8+csqoz9dzmua0i0z984=">aaab7hicbvbns8naej34wetx1aoxxslus0 w<latexit sha1_base64="gme7o Learning by Optimization Gradient Descent E(w) "51

52 <latexit sha1_base64="y1sga0hc1+vyvzud2bsehdxorhg=">aaab63icb <latexit sha1_base64="dhgzajuhkm6fz1n54zeef5aaur4=">aaab63icbvbns8n <latexit sha1_base64="dp <latexit sha1_base64="bf8kdamfcwhxbnbq2/som65km0i=">aaab63icbvbnswmxej2tx7v+vt16crahxsq <latexit sha1_base64="w7zcg9cyd8hi5p6sduv7uqvj5bg=">aaaci3icbvbds8mwfe3n9/ya+uhlcagtcbqikiiiiocjgvuatyzbln2csvusvbml/8ux/4ovpijiiw/+f9otoe4pbe7oufcm9/gxz0rb9odvmpqemz2bxygvli2vrfbw1psqsishdrlxslz9ujszkdy005y2y0lb+jy2/nvz3g/dualyfn7oyuw9af2qbyyanlk3cnzf0buoh0+wir7ew24fhadsbhji6sygnqool2r3o9n3na/nupwqxbdhwh+ju5aqkndvrby5vygkgoaacfcq49ix9tj8jue0k7ujojgqw+jtjqehckq8dlrjhren0snbjm0jnr6ppztseeonhw8qbeibmvry8t+vk+jgyetzgceahmt8ujbwrcocb4 Network Training Parameter Optimization by Gradient Descent Goal: Minimize E(w) cannot be solved analytically has many local minima Iterative optimization procedure w[0] let be the starting vector for the weights (initialization) w[t] is the weight vector in the t-th iteration gradient descent step: in iteration [t+1] update the weight vector: w[t + 1] - with learning rate or step size slide adapted from David Stutz "52

53 Network Training - Approaches slide taken from David Stutz "53

54 <latexit sha1_base64="w7zcg9cyd8hi5p6sduv7uqvj5bg=">aaaci3icbvbds8mwfe3n9/ya+uhlcagtcbqikiiiiocjgvuatyzbln2csvusvbml/8ux/4ovpijiiw/+f9otoe4pbe7oufcm9/gxz0rb9odvmpqemz2bxygvli2vrfbw1psqsishdrlxslz9ujszkdy005y2y0lb+jy2/nvz3g/dualyfn7oyuw9af2qbyyanlk3cnzf0buoh0+wir7ew24fhadsbhji6sygnqool2r3o9n3na/nupwqxbdhwh+ju5aqkndvrby5vygkgoaacfcq49ix9tj8jue0k7ujojgqw+jtjqehckq8dlrjhren0snbjm0jnr6ppztseeonhw8qbeibmvry8t+vk+jgyetzgceahmt8ujbwrcoc <latexit sha1_base64="1ddb+j8hnjc23veomsa2sh4ck2g=">aaab9hicb <latexit sha1_base64="ou7jv5ivmelq3e/mqatd1v9md0k=">aaacshicbzblswmxfiuz9v1fvzdugkwoigvgbn0oggguk1gvounwj83uajizkoxshvl5bly68ze4cagio9mhqnulgcn37r1jtprypo3rpjulsfgjyanpmfls3pzcymvp+vwnmsk0srkeqmsinovm0qzhhtplvfeqeacx0e1rz7+4o0qzrj6zbkodar3jykbawbrwwvuw2fscmgc3xvve4xsf3sew/sj4c/sdeakwhysguz+cmgw4pg4lrt1vfn9kzlqik1w37vyl/xxeuftrsbph5clvjyqtvbrcqeuw56ymyhvrcadf2c80tyhcqoe2rjqgqa7yfhafxrekjene2smn7tofezkirbsisp0czlue9xrwp6+vmxgvyjlmm0mlgvwuzxybbpdsxw2mkdg8awuqxexbmbkgm5wx2zdtcn7ol/+k8+2659a9053q4cewjmm0itzqdxlofx2ie9ratut <latexit sha1_base64="+kfq56y9+8ypkzn1gifexnnghyu=">aaacgxicbvdlssnafj3uv62vqks3g0vonyurqvdsemflbfuajibjdnkonuzczmrsqn7djb/ixouilnxl Backpropagation = Parameter Optimization by Gradient Descent General gradient descent step: w[t + 1] More specifically for weight w (l) ij w[t + 1] (l) ij = w[t](l) n (l) ij How to n (l) ij slide taken from David Stutz "54

55 <latexit sha1_base64="n6j4eskoxv3u/jrxk3h7gcpjxce=">aaacunicbvlps8mwgm3m7/lr6tflcajbwdgkobdf8ojrwelgnsxn0i0zauvyvamlf6mgxvxdvhhqs62tuflb4phe+74kl/eiwtvy1nuhode/sli0vfjaxvvf2cxvbd/qmfaunwgoqtx0igacb6wbharrroor6ql25z1cdps7r6y0d4mbsclwlqqbcj9taozyyzxx+x1afbumn2ifo4l5umxpv6sjelchtunr0bf00/6pld2ncma7sgtzhp/clpezvc1x+2nlpmitv6y6nsw8c+wcvfbev2751emenjysacqi1i3biqcdegwccpavnfizinah0mutawmimw6nw0gyvg+ydvzdzvyaemhodqreap1izzglgz6e1gbkf1orbv+knfigioefdlsrhwsmir7kiztcmqoimybqxc1zme0rrsiyvyizeozpk8+c28o6bdxt66pk+vkexzlarxuoimx0jm7rjbpcdut <latexit sha1_base64="+iikcj4/nkyieeacrqeqqj47njs=">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</latexit> <latexit sha1_base64="dwe0w8sr6q7ahp4hwop6rlczcju=">aaackhicbvdlssnafj34rpuvdelmsajtwpkiobu14mzlbfuanobjdnjoo3kwm1fiyoe48vfcicjsrv/ipa2orqcgzj3nxu7c44smcmkyy21hcwl5zbwwvlzf2nza1nd2mykiocynhlcatx0kckm+augqgwmhncdpya <latexit sha1_base64="xe6esrqbwrgdcp+boog7ktkbnr0=">aaacm3icbzdlssnafiyn9vbrrerszwar2ouleue3skeecvxbxqcpytkdtnnojmfmyikh7+tgf3ehiatf3poottqc2vrdwm93zuhm+d2qualm88xilcwula9kv3nr6xubw/ntnbomiofjdqcsee0xsciojzvffspnubdku4w03mffwm/ceyfpwg/vkcrth3u59shgsimnf217auhydpfqfdf46fdisjt8gket035yfxdzkunggbq7hcnk0ambi6efukorldj5glk2x4lzxpqaapiq Backpropagation = Parameter Optimization by Gradient Descent Remember: y (l) i = f z (l) i = f m (l 1) X j=0 w (l) ij y(l 1) j 1 A Using chain rule: dropping [t] for n (l) ij (l) (l) (l) ij := (l) (l) (l) ij Second (l) (l) ij (l 1) = y j n (l) ij = (l) (l 1) i y j "55

56 <latexit sha1_base64="vmmz4pzxtbmsbj/g+yunxvf98us=">aaacjnichvfds8mwfe3r19z8qpros3aig8jorvsu6uaeh3yy4d5gnsxn0i2ypivjlvn6c/xdvvlvzozgc1o8edicc25ucq4fmyqvbx8a5tlyyupabj1f2njc2rz2dpsysgqmdryxslr9jamjndquvyy0y0fq6dps8p9vrnrrhqhji/6ohjhphqjpauaxupryrhe3r5hchn1ks/dhtjmdf1ui3uagnloxeooibm89xnotz1piberpypvf+3dwdvnz9ln1jxgevbqr9rjginamoagmvfesd7cx4sqkxgggpow4dqy66ehuzeiwdxnjyosfuz90noqojlkbjupm4kfmejcihd5cwte725giumph6gtninrazmsj8jetk6jgvjtshiekcpw9kegyvbec7qb2qcbysaegcauq3wrxaomwln5gxofgzh95etspk45dcr5oirwrsrw5sa8oqak44azuwb2ogwbarsfwj <latexit sha1_base64="risbdnzg0uyft2tsppjxrggqt1u=">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</latexit> <latexit sha1_base64="fjnbw2rmlltusd5me5n3amt7ipu=">aaacqhicbzc7swnbemb34ju+opy2i0fiemkdcnoogo2fhyixqu5y7g3mkiv7d3bnhhjkt7pxt7cztrfqxnbktqwyhwmlh983w8z+glqkjbb9abwmpmdm5+yxiotlyyurpbx1k51kikodjzjr1whtieumdrqo4tpvwkjaqiponqzzxg0olzl4evspebhrxciunkgx/flddrxjuzsyhyjj2vdfk6+c7tjvwedbvz1w6senw26qratulrbiztkmrhkdllb9ut <latexit sha1_base64="lhermcp9fj2t27uwysvwaoutovg=">aaaconicbvbnaxsxfnsmazu6x05zzexufna0nsttac6g0fdiiyceajvgxs9awwsla7wl9dbpivz35zjfkvspvftqehlnd4js+jamhramm294epmuuhgigl/e2pp1p8+eb7xovhz1+s3b5ua7gcllzxif5tlxxwk1xarf+yba8uncc5olkg+t+d7ch55wbusufkbv8cijuyvswsg4kw4efy+vf9rgprymmjjlatutmq5nmcvw9eg93soh5cn4uirf2pohh0m79n/g6pnlfcyqwyuwas2mm2ipuzhutojosar+tmiktnakh3hzipzkrmy4aiapmsmsfbbzqkewyetgwbpeudanuz5yvngmm8gut6/xb6dmcjpr9xtgpxo/ywlmtjulbjkjmdmpvyx4p29uqrotwagkerhid4vsumli8ajhpbgam5cvi5rp4f6k2yy6csg13xalkicnpyadbocehxl0pbx7bvxhbtpg75g Backpropagation = Parameter Optimization by Gradient Descent First term for output layer: with (L+1) i sum-of-squared error n (L+1) i = (L+1) i E n (w) = 1 2 apple P i=1 y (L+1) i (x n,w) t ni = y i (x n,w) t (L+1) i (L+1) i CX (L+1) (L+1) i y (L+1) i (x n,w) t ni 2 = y (L+1) i (x n,w) t (L+1) (L+1) i = f 0 z (L+1) i "56

57 <latexit sha1_base64="uxnukpp993462mzygv6tprmfp94=">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</latexit> <latexit sha1_base64="elmf0crwayi7eutjtaasaymfpic=">aaab+hicbvbns8naej3ur1 <latexit sha1_base64="a/qtmvgdfbdzulf4fwrq88i3k7e=">aaacahicbzdlssnafizpvnz6i7pw4wawcbwhj <latexit sha1_base64="lrq/hp7kvqnkbjti4j8nxe5hmia=">aaab+nicbvbns8naen34wetxqkcvi0woccurqu9s8olbqwx7a Backpropagation = Parameter Optimization by Gradient Descent First term for all other layers: (l) i (l) i m X (l+1) = f 0 z (l) i this can be evaluated recursively starting with the output layer L+1: j=1 w (l+1) ji (l+1) j (L+1) i w (l+1) 1i w (l+1) m (l+1) i "57

58 <latexit sha1_base64="xe6esrqbwrgdcp+boog7ktkbnr0=">aaacm3icbzdlssnafiyn9vbrrerszwar2ouleue3skeecvxbxqcpytkdtnnojmfmyikh7+tgf3ehiatf3poottqc2vrdwm93zuhm+d2qualm88xilcwula9kv3nr6xubw/ntnbomiofjdqcsee0xsciojzvffspnubdku4w03mffwm/ceyfpwg/vkcrth3u59shgsimnf217auhydpfqfdf46fdisjt8gket035yfxdzkunggbq7hcnk0ambi6efukorldj5glk2x4lzxpqaapiq6u <latexit sha1_base64="ou7jv5ivmelq3e/mqatd1v9md0k=">aaacshicbzblswmxfiuz9v1fvzdugkwoigvgbn0oggguk1gvounwj83uajizkoxshvl5bly68ze4cagio9mhqnulgcn37r1jtprypo3rpjulsfgjyanpmfls3pzcymvp+vwnmsk0srkeqmsinovm0qzhhtplvfeqeacx0e1rz7+4o0qzrj6zbkodar3jykbawbrwwvuw2fscmgc3xvve4xsf3sew/sj4c/sdeakwhysguz+cmgw4pg4lrt1vfn9kzlqik1w37vyl/xxeuftrsbph5clvjyqtvbrcqeuw56ymyhvrcadf2c80tyhcqoe2rjqgqa7yfhafxrekjene2smn7tofezkirbsisp0czlue9xrwp6+vmxgvyjlmm0mlgvwuzxybbpdsxw2mkdg8awuqxexbmbkgm5wx2zdtcn7ol/+k8+2659a9053q4cewjmm0itzqdxlofx2ie9ratutq Backpropagation = Parameter Optimization by Gradient Descent determine the required derivatives using: use derivatives to update all weights in iteration [t+1] : w[t + 1] (l) n (l) ij = w[t](l) ij = (l) (l 1) i y n (l) ij "58

59 Gradient & Training Only two things need to be implemented to define new layer: forward pass error back propagation Watch overfitting loss/energy test validation train epochs "59

60 Gradient & Training Only two things need to be implemented to define new layer: forward pass error back propagation Watch overfitting loss/energy test validation train epochs "60

61 Gradient & Training Only two things need to be implemented to define new layer: forward pass error back propagation Watch overfitting loss/energy test validation train epochs "61

62 Overview Today Recent successes of Deep Learning necessarily incomplete What is Deep Learning? Neural network basics Supervised learning with error backpropagation [reading Bishop chapter ] Convolutional Neural Networks "62

63 Overview of Deep Learning "63

64 Multistage Hubel&Wiesel Architecture Slide: Y.LeCun [Hubel & Wiesel 1962] simple cells detect local features complex cells pool the outputs of simple cells within a retinotopic neighborhood. Cognitron / Neocognitron [Fukushima ] Also HMAX [Poggio ] Convolutional Networks [LeCun 1988-present]

65 Convolutional Neural Networks LeCun et al Neural network with specialized connectivity structure

66 Convnet Successes Handwritten text/digits MNIST (0.17% error [Ciresan et al. 2011]) Arabic & Chinese [Ciresan et al. 2012] Simpler recognition benchmarks CIFAR-10 (9.3% error [Wan et al. 2013]) Traffic sign recognition 0.56% error vs 1.16% for humans [Ciresan et al. 2011] But (until recently) less good at more complex datasets E.g. Caltech-101/256 (few training examples)

67 Characteristics of Convnets Feed-forward: Convolve input Non-linearity (rectified linear) Pooling (local max) / (=subsampling) Supervised Train convolutional filters by back-propagating classification error Feature maps Pooling Non-linearity Convolution (Learned) Input Image [LeCun et al. 1989]

68 68

69 69

70 70

71 71

72 72

73 73

74 74

75 Characteristics of Convnets Feed-forward: Convolve input Non-linearity (rectified linear) Pooling (local max) / (=subsampling) Supervised Train convolutional filters by back-propagating classification error Feature maps Pooling Non-linearity Convolution (Learned) Input Image [LeCun et al. 1989]

76 Application to ImageNet [Deng et al. CVPR 2009] used 1.2 million images of 1000 labeled classes (overall ~ 14 million labeled images, 20k classes) Images gathered from Internet Human labels via Amazon Turk [NIPS 2012]

77 Krizhevsky et al. [NIPS2012] Same model as LeCun 98 but: - Bigger model (8 layers) - More data (10 6 vs 10 3 images) - GPU implementation (50x speedup over CPU) - Better regularization (DropOut) 7 hidden layers, 650,000 neurons, 60,000,000 parameters Trained on 2 GPUs for a week

78 ImageNet Classification 2012 Krizhevsky et al % error (top-5) Next best (non-convnet) 26.2% error Top-5 error rate % SuperVision ISI Oxford INRIA Amsterdam

79 Commercial Deployment Google & Baidu, Spring 2013 for personal image search

Deep Neural Networks:

Deep Neural Networks: Deep Neural Networks: Part II Convolutional Neural Network (CNN) Yuan-Kai Wang, 2016 Web site of this course: http://pattern-recognition.weebly.com source: CNN for ImageClassification, by S. Lazebnik,

More information

CS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016

CS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 CS 2750: Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 Plan for today Neural network definition and examples Training neural networks (backprop) Convolutional

More information

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech Convolutional Neural Networks Computer Vision Jia-Bin Huang, Virginia Tech Today s class Overview Convolutional Neural Network (CNN) Training CNN Understanding and Visualizing CNN Image Categorization:

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning for Object Categorization 14.01.2016 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period

More information

Deep Learning for Computer Vision II

Deep Learning for Computer Vision II IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L

More information

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU, Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image

More information

CS 1674: Intro to Computer Vision. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 16, 2016

CS 1674: Intro to Computer Vision. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 16, 2016 CS 1674: Intro to Computer Vision Neural Networks Prof. Adriana Kovashka University of Pittsburgh November 16, 2016 Announcements Please watch the videos I sent you, if you haven t yet (that s your reading)

More information

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides Deep Learning in Visual Recognition Thanks Da Zhang for the slides Deep Learning is Everywhere 2 Roadmap Introduction Convolutional Neural Network Application Image Classification Object Detection Object

More information

Part-Based Models for Object Class Recognition Part 3

Part-Based Models for Object Class Recognition Part 3 High Level Computer Vision! Part-Based Models for Object Class Recognition Part 3 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de! http://www.d2.mpi-inf.mpg.de/cv ! State-of-the-Art

More information

ImageNet Classification with Deep Convolutional Neural Networks

ImageNet Classification with Deep Convolutional Neural Networks ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky Ilya Sutskever Geoffrey Hinton University of Toronto Canada Paper with same name to appear in NIPS 2012 Main idea Architecture

More information

INTRODUCTION TO DEEP LEARNING

INTRODUCTION TO DEEP LEARNING INTRODUCTION TO DEEP LEARNING CONTENTS Introduction to deep learning Contents 1. Examples 2. Machine learning 3. Neural networks 4. Deep learning 5. Convolutional neural networks 6. Conclusion 7. Additional

More information

Spatial Localization and Detection. Lecture 8-1

Spatial Localization and Detection. Lecture 8-1 Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday

More information

Progress in Computer Vision in the Last Decade & Open Problems: People Detection & Human Pose Estimation

Progress in Computer Vision in the Last Decade & Open Problems: People Detection & Human Pose Estimation Progress in Computer Vision in the Last Decade & Open Problems: People Detection & Human Pose Estimation Bernt Schiele Max Planck Institute for Informatics & Saarland University, Saarland Informatics Campus

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

COMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017

COMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017 COMP9444 Neural Networks and Deep Learning 7. Image Processing COMP9444 17s2 Image Processing 1 Outline Image Datasets and Tasks Convolution in Detail AlexNet Weight Initialization Batch Normalization

More information

Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group

Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group 1D Input, 1D Output target input 2 2D Input, 1D Output: Data Distribution Complexity Imagine many dimensions (data occupies

More information

Part-Based Models for Object Class Recognition Part 2

Part-Based Models for Object Class Recognition Part 2 High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object

More information

Part-Based Models for Object Class Recognition Part 2

Part-Based Models for Object Class Recognition Part 2 High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object

More information

Learning-based Methods in Vision

Learning-based Methods in Vision Learning-based Methods in Vision 16-824 Sparsity and Deep Learning Motivation Multitude of hand-designed features currently in use in vision - SIFT, HoG, LBP, MSER, etc. Even the best approaches, just

More information

Deep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies

Deep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies http://blog.csdn.net/zouxy09/article/details/8775360 Automatic Colorization of Black and White Images Automatically Adding Sounds To Silent Movies Traditionally this was done by hand with human effort

More information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 551 Applied Machine Learning Lecture 16: Deep Learning COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all

More information

Lecture 17: Neural Networks and Deep Learning. Instructor: Saravanan Thirumuruganathan

Lecture 17: Neural Networks and Deep Learning. Instructor: Saravanan Thirumuruganathan Lecture 17: Neural Networks and Deep Learning Instructor: Saravanan Thirumuruganathan Outline Perceptron Neural Networks Deep Learning Convolutional Neural Networks Recurrent Neural Networks Auto Encoders

More information

Introduction to Neural Networks

Introduction to Neural Networks Introduction to Neural Networks Jakob Verbeek 2017-2018 Biological motivation Neuron is basic computational unit of the brain about 10^11 neurons in human brain Simplified neuron model as linear threshold

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University.

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University. Visualizing and Understanding Convolutional Networks Christopher Pennsylvania State University February 23, 2015 Some Slide Information taken from Pierre Sermanet (Google) presentation on and Computer

More information

Object Recognition II

Object Recognition II Object Recognition II Linda Shapiro EE/CSE 576 with CNN slides from Ross Girshick 1 Outline Object detection the task, evaluation, datasets Convolutional Neural Networks (CNNs) overview and history Region-based

More information

Image and Video Understanding

Image and Video Understanding Image and Video Understanding 2VO 70.095 WS Christoph Feichtenhofer, Axel Pinz Slide credits: Many thanks to all the great computer vision researchers on which this presentation relies on. Most material

More information

SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic

SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic SEMANTIC COMPUTING Lecture 8: Introduction to Deep Learning Dagmar Gromann International Center For Computational Logic TU Dresden, 7 December 2018 Overview Introduction Deep Learning General Neural Networks

More information

Neural Networks and Deep Learning

Neural Networks and Deep Learning Neural Networks and Deep Learning Example Learning Problem Example Learning Problem Celebrity Faces in the Wild Machine Learning Pipeline Raw data Feature extract. Feature computation Inference: prediction,

More information

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Syllabus 1. Whole traditional (old) visual recognition pipeline 2. Introduction to Neural Nets 3. Deep Nets for image classification To do : Voir la leçon inaugurale

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Announcements Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Seminar registration period starts on Friday We will offer a lab course in the summer semester Deep Robot Learning Topic:

More information

Deep Learning Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD.

Deep Learning Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD. Deep Learning 861.061 Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD asan.agibetov@meduniwien.ac.at Medical University of Vienna Center for Medical Statistics,

More information

Advanced Introduction to Machine Learning, CMU-10715

Advanced Introduction to Machine Learning, CMU-10715 Advanced Introduction to Machine Learning, CMU-10715 Deep Learning Barnabás Póczos, Sept 17 Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio

More information

Yiqi Yan. May 10, 2017

Yiqi Yan. May 10, 2017 Yiqi Yan May 10, 2017 P a r t I F u n d a m e n t a l B a c k g r o u n d s Convolution Single Filter Multiple Filters 3 Convolution: case study, 2 filters 4 Convolution: receptive field receptive field

More information

Machine Learning. MGS Lecture 3: Deep Learning

Machine Learning. MGS Lecture 3: Deep Learning Dr Michel F. Valstar http://cs.nott.ac.uk/~mfv/ Machine Learning MGS Lecture 3: Deep Learning Dr Michel F. Valstar http://cs.nott.ac.uk/~mfv/ WHAT IS DEEP LEARNING? Shallow network: Only one hidden layer

More information

Artificial Neural Networks. Introduction to Computational Neuroscience Ardi Tampuu

Artificial Neural Networks. Introduction to Computational Neuroscience Ardi Tampuu Artificial Neural Networks Introduction to Computational Neuroscience Ardi Tampuu 7.0.206 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition

More information

YOLO9000: Better, Faster, Stronger

YOLO9000: Better, Faster, Stronger YOLO9000: Better, Faster, Stronger Date: January 24, 2018 Prepared by Haris Khan (University of Toronto) Haris Khan CSC2548: Machine Learning in Computer Vision 1 Overview 1. Motivation for one-shot object

More information

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia Deep learning for dense per-pixel prediction Chunhua Shen The University of Adelaide, Australia Image understanding Classification error Convolution Neural Networks 0.3 0.2 0.1 Image Classification [Krizhevsky

More information

CSE 559A: Computer Vision

CSE 559A: Computer Vision CSE 559A: Computer Vision Fall 2018: T-R: 11:30-1pm @ Lopata 101 Instructor: Ayan Chakrabarti (ayan@wustl.edu). Course Staff: Zhihao Xia, Charlie Wu, Han Liu http://www.cse.wustl.edu/~ayan/courses/cse559a/

More information

Introduction to Neural Networks

Introduction to Neural Networks Introduction to Neural Networks Machine Learning and Object Recognition 2016-2017 Course website: http://thoth.inrialpes.fr/~verbeek/mlor.16.17.php Biological motivation Neuron is basic computational unit

More information

Structured Prediction using Convolutional Neural Networks

Structured Prediction using Convolutional Neural Networks Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer

More information

Know your data - many types of networks

Know your data - many types of networks Architectures Know your data - many types of networks Fixed length representation Variable length representation Online video sequences, or samples of different sizes Images Specific architectures for

More information

All You Want To Know About CNNs. Yukun Zhu

All You Want To Know About CNNs. Yukun Zhu All You Want To Know About CNNs Yukun Zhu Deep Learning Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image

More information

Learning. Learning agents Inductive learning. Neural Networks. Different Learning Scenarios Evaluation

Learning. Learning agents Inductive learning. Neural Networks. Different Learning Scenarios Evaluation Learning Learning agents Inductive learning Different Learning Scenarios Evaluation Slides based on Slides by Russell/Norvig, Ronald Williams, and Torsten Reil Material from Russell & Norvig, chapters

More information

Inception and Residual Networks. Hantao Zhang. Deep Learning with Python.

Inception and Residual Networks. Hantao Zhang. Deep Learning with Python. Inception and Residual Networks Hantao Zhang Deep Learning with Python https://en.wikipedia.org/wiki/residual_neural_network Deep Neural Network Progress from Large Scale Visual Recognition Challenge (ILSVRC)

More information

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Tutorial on Keras CAP 6412 - ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Deep learning packages TensorFlow Google PyTorch Facebook AI research Keras Francois Chollet (now at Google) Chainer Company

More information

Study of Residual Networks for Image Recognition

Study of Residual Networks for Image Recognition Study of Residual Networks for Image Recognition Mohammad Sadegh Ebrahimi Stanford University sadegh@stanford.edu Hossein Karkeh Abadi Stanford University hosseink@stanford.edu Abstract Deep neural networks

More information

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract

More information

Convolutional Neural Networks + Neural Style Transfer. Justin Johnson 2/1/2017

Convolutional Neural Networks + Neural Style Transfer. Justin Johnson 2/1/2017 Convolutional Neural Networks + Neural Style Transfer Justin Johnson 2/1/2017 Outline Convolutional Neural Networks Convolution Pooling Feature Visualization Neural Style Transfer Feature Inversion Texture

More information

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images Marc Aurelio Ranzato Yann LeCun Courant Institute of Mathematical Sciences New York University - New York, NY 10003 Abstract

More information

DL Tutorial. Xudong Cao

DL Tutorial. Xudong Cao DL Tutorial Xudong Cao Historical Line 1960s Perceptron 1980s MLP BP algorithm 2006 RBM unsupervised learning 2012 AlexNet ImageNet Comp. 2014 GoogleNet VGGNet ImageNet Comp. Rule based AI algorithm Game

More information

Simplifying ConvNets for Fast Learning

Simplifying ConvNets for Fast Learning Simplifying ConvNets for Fast Learning Franck Mamalet 1 and Christophe Garcia 2 1 Orange Labs, 4 rue du Clos Courtel, 35512 Cesson-Sévigné, France, franck.mamalet@orange.com 2 LIRIS, CNRS, Insa de Lyon,

More information

Convolutional Neural Networks

Convolutional Neural Networks Lecturer: Barnabas Poczos Introduction to Machine Learning (Lecture Notes) Convolutional Neural Networks Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications.

More information

International Journal of Computer Engineering and Applications, Volume XII, Special Issue, September 18,

International Journal of Computer Engineering and Applications, Volume XII, Special Issue, September 18, REAL-TIME OBJECT DETECTION WITH CONVOLUTION NEURAL NETWORK USING KERAS Asmita Goswami [1], Lokesh Soni [2 ] Department of Information Technology [1] Jaipur Engineering College and Research Center Jaipur[2]

More information

Weakly Supervised Object Recognition with Convolutional Neural Networks

Weakly Supervised Object Recognition with Convolutional Neural Networks GDR-ISIS, Paris March 20, 2015 Weakly Supervised Object Recognition with Convolutional Neural Networks Ivan Laptev ivan.laptev@inria.fr WILLOW, INRIA/ENS/CNRS, Paris Joint work with: Maxime Oquab Leon

More information

Multi-Glance Attention Models For Image Classification

Multi-Glance Attention Models For Image Classification Multi-Glance Attention Models For Image Classification Chinmay Duvedi Stanford University Stanford, CA cduvedi@stanford.edu Pararth Shah Stanford University Stanford, CA pararth@stanford.edu Abstract We

More information

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Part II: Visual Features and Representations Liangliang Cao, IBM Watson Research Center Evolvement of Visual Features

More information

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro CMU 15-781 Lecture 18: Deep learning and Vision: Convolutional neural networks Teacher: Gianni A. Di Caro DEEP, SHALLOW, CONNECTED, SPARSE? Fully connected multi-layer feed-forward perceptrons: More powerful

More information

Convolutional Neural Networks. CSC 4510/9010 Andrew Keenan

Convolutional Neural Networks. CSC 4510/9010 Andrew Keenan Convolutional Neural Networks CSC 4510/9010 Andrew Keenan Neural network to Convolutional Neural Network 0.4 0.7 0.3 Neural Network Basics 0.4 0.7 0.3 Individual Neuron Network Backpropagation 1. 2. 3.

More information

Deep Learning for Vision: Tricks of the Trade

Deep Learning for Vision: Tricks of the Trade Deep Learning for Vision: Tricks of the Trade Marc'Aurelio Ranzato Facebook, AI Group www.cs.toronto.edu/~ranzato BAVM Friday, 4 October 2013 Ideal Features Ideal Feature Extractor - window, right - chair,

More information

DEEP NEURAL NETWORKS FOR OBJECT DETECTION

DEEP NEURAL NETWORKS FOR OBJECT DETECTION DEEP NEURAL NETWORKS FOR OBJECT DETECTION Sergey Nikolenko Steklov Institute of Mathematics at St. Petersburg October 21, 2017, St. Petersburg, Russia Outline Bird s eye overview of deep learning Convolutional

More information

Introduction to Deep Learning

Introduction to Deep Learning ENEE698A : Machine Learning Seminar Introduction to Deep Learning Raviteja Vemulapalli Image credit: [LeCun 1998] Resources Unsupervised feature learning and deep learning (UFLDL) tutorial (http://ufldl.stanford.edu/wiki/index.php/ufldl_tutorial)

More information

Deep neural networks II

Deep neural networks II Deep neural networks II May 31 st, 2018 Yong Jae Lee UC Davis Many slides from Rob Fergus, Svetlana Lazebnik, Jia-Bin Huang, Derek Hoiem, Adriana Kovashka, Why (convolutional) neural networks? State of

More information

Ryerson University CP8208. Soft Computing and Machine Intelligence. Naive Road-Detection using CNNS. Authors: Sarah Asiri - Domenic Curro

Ryerson University CP8208. Soft Computing and Machine Intelligence. Naive Road-Detection using CNNS. Authors: Sarah Asiri - Domenic Curro Ryerson University CP8208 Soft Computing and Machine Intelligence Naive Road-Detection using CNNS Authors: Sarah Asiri - Domenic Curro April 24 2016 Contents 1 Abstract 2 2 Introduction 2 3 Motivation

More information

arxiv: v1 [cs.cv] 6 Jul 2016

arxiv: v1 [cs.cv] 6 Jul 2016 arxiv:607.079v [cs.cv] 6 Jul 206 Deep CORAL: Correlation Alignment for Deep Domain Adaptation Baochen Sun and Kate Saenko University of Massachusetts Lowell, Boston University Abstract. Deep neural networks

More information

Deep Learning Workshop. Nov. 20, 2015 Andrew Fishberg, Rowan Zellers

Deep Learning Workshop. Nov. 20, 2015 Andrew Fishberg, Rowan Zellers Deep Learning Workshop Nov. 20, 2015 Andrew Fishberg, Rowan Zellers Why deep learning? The ImageNet Challenge Goal: image classification with 1000 categories Top 5 error rate of 15%. Krizhevsky, Alex,

More information

Lecture 20: Neural Networks for NLP. Zubin Pahuja

Lecture 20: Neural Networks for NLP. Zubin Pahuja Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple

More information

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Deep learning for object detection. Slides from Svetlana Lazebnik and many others Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep

More information

Logical Rhythm - Class 3. August 27, 2018

Logical Rhythm - Class 3. August 27, 2018 Logical Rhythm - Class 3 August 27, 2018 In this Class Neural Networks (Intro To Deep Learning) Decision Trees Ensemble Methods(Random Forest) Hyperparameter Optimisation and Bias Variance Tradeoff Biological

More information

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Qi Zhang & Yan Huang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition

More information

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:

More information

Video Object Segmentation using Deep Learning

Video Object Segmentation using Deep Learning Video Object Segmentation using Deep Learning Update Presentation, Week 3 Zack While Advised by: Rui Hou, Dr. Chen Chen, and Dr. Mubarak Shah June 2, 2017 Youngstown State University 1 Table of Contents

More information

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017 3/0/207 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/0/207 Perceptron as a neural

More information

IMPLEMENTING DEEP LEARNING USING CUDNN 이예하 VUNO INC.

IMPLEMENTING DEEP LEARNING USING CUDNN 이예하 VUNO INC. IMPLEMENTING DEEP LEARNING USING CUDNN 이예하 VUNO INC. CONTENTS Deep Learning Review Implementation on GPU using cudnn Optimization Issues Introduction to VUNO-Net DEEP LEARNING REVIEW BRIEF HISTORY OF NEURAL

More information

Deep Learning & Neural Networks

Deep Learning & Neural Networks Deep Learning & Neural Networks Machine Learning CSE4546 Sham Kakade University of Washington November 29, 2016 Sham Kakade 1 Announcements: HW4 posted Poster Session Thurs, Dec 8 Today: Review: EM Neural

More information

Dynamic Routing Between Capsules

Dynamic Routing Between Capsules Report Explainable Machine Learning Dynamic Routing Between Capsules Author: Michael Dorkenwald Supervisor: Dr. Ullrich Köthe 28. Juni 2018 Inhaltsverzeichnis 1 Introduction 2 2 Motivation 2 3 CapusleNet

More information

Deep Learning & Feature Learning Methods for Vision

Deep Learning & Feature Learning Methods for Vision Deep Learning & Feature Learning Methods for Vision CVPR 2012 Tutorial: 9am-5:30pm Rob Fergus (NYU) Kai Yu (Baidu) Marc Aurelio Ranzato (Google) Honglak Lee (Michigan) Ruslan Salakhutdinov (U. Toronto)

More information

Deconvolutions in Convolutional Neural Networks

Deconvolutions in Convolutional Neural Networks Overview Deconvolutions in Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Deconvolutions in CNNs Applications Network visualization

More information

CS 523: Multimedia Systems

CS 523: Multimedia Systems CS 523: Multimedia Systems Angus Forbes creativecoding.evl.uic.edu/courses/cs523 Today - Convolutional Neural Networks - Work on Project 1 http://playground.tensorflow.org/ Convolutional Neural Networks

More information

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the

More information

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

Deformable Part Models

Deformable Part Models CS 1674: Intro to Computer Vision Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 9, 2016 Today: Object category detection Window-based approaches: Last time: Viola-Jones

More information

Character Recognition Using Convolutional Neural Networks

Character Recognition Using Convolutional Neural Networks Character Recognition Using Convolutional Neural Networks David Bouchain Seminar Statistical Learning Theory University of Ulm, Germany Institute for Neural Information Processing Winter 2006/2007 Abstract

More information

Deep Learning. Volker Tresp Summer 2014

Deep Learning. Volker Tresp Summer 2014 Deep Learning Volker Tresp Summer 2014 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there

More information

Weighted Convolutional Neural Network. Ensemble.

Weighted Convolutional Neural Network. Ensemble. Weighted Convolutional Neural Network Ensemble Xavier Frazão and Luís A. Alexandre Dept. of Informatics, Univ. Beira Interior and Instituto de Telecomunicações Covilhã, Portugal xavierfrazao@gmail.com

More information

Single Image Depth Estimation via Deep Learning

Single Image Depth Estimation via Deep Learning Single Image Depth Estimation via Deep Learning Wei Song Stanford University Stanford, CA Abstract The goal of the project is to apply direct supervised deep learning to the problem of monocular depth

More information

High Level Computer Vision

High Level Computer Vision High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de http://www.d2.mpi-inf.mpg.de/cv Please Note No

More information

Flow-Based Video Recognition

Flow-Based Video Recognition Flow-Based Video Recognition Jifeng Dai Visual Computing Group, Microsoft Research Asia Joint work with Xizhou Zhu*, Yuwen Xiong*, Yujie Wang*, Lu Yuan and Yichen Wei (* interns) Talk pipeline Introduction

More information

Global Optimality in Neural Network Training

Global Optimality in Neural Network Training Global Optimality in Neural Network Training Benjamin D. Haeffele and René Vidal Johns Hopkins University, Center for Imaging Science. Baltimore, USA Questions in Deep Learning Architecture Design Optimization

More information

LSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University

LSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University LSTM and its variants for visual recognition Xiaodan Liang xdliang328@gmail.com Sun Yat-sen University Outline Context Modelling with CNN LSTM and its Variants LSTM Architecture Variants Application in

More information

Neural Network Neurons

Neural Network Neurons Neural Networks Neural Network Neurons 1 Receives n inputs (plus a bias term) Multiplies each input by its weight Applies activation function to the sum of results Outputs result Activation Functions Given

More information

Category Recognition. Jia-Bin Huang Virginia Tech ECE 6554 Advanced Computer Vision

Category Recognition. Jia-Bin Huang Virginia Tech ECE 6554 Advanced Computer Vision Category Recognition Jia-Bin Huang Virginia Tech ECE 6554 Advanced Computer Vision Administrative stuffs Presentation and discussion leads assigned https://docs.google.com/spreadsheets/d/1p5pfycio5flq

More information

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling [DOI: 10.2197/ipsjtcva.7.99] Express Paper Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling Takayoshi Yamashita 1,a) Takaya Nakamura 1 Hiroshi Fukui 1,b) Yuji

More information

DEEP LEARNING REVIEW. Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature Presented by Divya Chitimalla

DEEP LEARNING REVIEW. Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature Presented by Divya Chitimalla DEEP LEARNING REVIEW Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature 2015 -Presented by Divya Chitimalla What is deep learning Deep learning allows computational models that are composed of multiple

More information

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center Machine Learning With Python Bin Chen Nov. 7, 2017 Research Computing Center Outline Introduction to Machine Learning (ML) Introduction to Neural Network (NN) Introduction to Deep Learning NN Introduction

More information

Como funciona o Deep Learning

Como funciona o Deep Learning Como funciona o Deep Learning Moacir Ponti (com ajuda de Gabriel Paranhos da Costa) ICMC, Universidade de São Paulo Contact: www.icmc.usp.br/~moacir moacir@icmc.usp.br Uberlandia-MG/Brazil October, 2017

More information

Supervised Hashing for Image Retrieval via Image Representation Learning

Supervised Hashing for Image Retrieval via Image Representation Learning Supervised Hashing for Image Retrieval via Image Representation Learning Rongkai Xia, Yan Pan, Cong Liu (Sun Yat-Sen University) Hanjiang Lai, Shuicheng Yan (National University of Singapore) Finding Similar

More information

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart

Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider

More information

Mocha.jl. Deep Learning in Julia. Chiyuan Zhang CSAIL, MIT

Mocha.jl. Deep Learning in Julia. Chiyuan Zhang CSAIL, MIT Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning with multi-layer (3~30) neural networks, on a huge training set. State-of-the-art on many AI tasks Computer Vision:

More information