Learning Convolutional Feature Hierarchies for Visual Recognition
|
|
- Nathan Welch
- 6 years ago
- Views:
Transcription
1 Learning Convolutional Feature Hierarchies for Visual Recognition Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau, Karol Gregor, Michael Mathieu, Yann LeCun Computer Science Department Courant Institute of Mathematical Sciences New York University
2 Overview Feature Extractors Unsupervised Feature Learning Sparse Coding Convolutional Sparse Coding Efficient Predictors for Recognition Hierarchical Object Recognition
3 Object Recognition Feature Extraction Gabor, SIFT, HoG, Color, combinations... Classification PMK-SVM, Linear,... Grauman 05, Lazebnik 06, Serre 05, Mutch 06,...
4 Object Recognition Feature Extractor Classifier It would be better to learn everything adaptive to different domains Learn feature extractor and classifier together
5 Feature Extraction Filterbank Non-lin pooling Can be based on unsupervised learning Should be efficient to extract features Overcomplete sparse representations are easily separable Conventional sparse coding is slow
6 Sparse Coding Represent an input vector using an overcomplete dictionary y i X D j 0 D j i D z j # of dictionary elements > size of input # of zero elements > > > # of non-zero Input Dictionary z Representation (sparse) Each X is represented using a linear combination of columns of D How do we calculate z for a given X? How do we learn D?
7 Sparse Coding 1) Find the sparsest solution that satisfies a given reconstruction error min z 0 s.t. x i D i z i 2 2 2) Find the best k-sparse representation that minimizes reconstruction error min x i D i z i 2 2 s.t. z 0 = k L0 minimization requires search not tractable
8 Sparse Coding Matching Pursuit Algorithms offer greedy solution [Mallat and Zhang 93] Greedily pick the dictionary element that reduces residual most very fast, but unstable Function MP (Y,D,n) R=Y,z=0 for k=1..n i = argmax(d T R) z_i = D it R R end = R - z_i D i
9 Sparse Coding min 1 2 x Dz2 2 + λ i z i Input Code Dictionary Sparsity D is given, search for optimal z Reconstruction + Sparsity A mapping f : x z For every input x optimization required to get z Chen 98, Beck 09, Li 09
10 Sparse Modeling min 1 2 x Dz2 2 + λ i z i Learn from data D has to be bounded to avoid trivial solutions Online or batch algorithms for updating dictionary Learn mapping f D : x z Olshausen and Field 97, Aharon 06, Lee 07, Ranzato 07, Kavukcuoglu 08, Zeiler 10,...
11 Per sample energy Sparse Modeling E(x, z, D) =min 1 2 x Dz2 2 + λ i z i Loss L(x, D) = 1 X x X E(x, z, D) For each sample, 1. do inference minimize E(x,z,D) wrt z (sparse coding) 2. update parameters D D η E D 3. Constrain elements of D to be unit norm
12 Sparse Modeling Two problems 1. Inference takes long time Train a predictor function 2. Patch based modeling produces redundant features Use convolutional sparse modeling
13 Predictive Sparse Decomposition min 1 2 x Dz2 2 + λ i z i + z C(x; K) 2 2 z j = g j tanh(k j x) Learning For each sample from data, do: 1. Fix K and D, minimize to get optimal z 2. Using the optimal value of z update D and K 3. Scale elements of D to be unit norm.
14 Predictive Sparse Decomposition Encoder (K) Decoder (D) 12x12 image patches 256 dictionary elements
15 Predictive Sparse Decomposition Encoder (k) Decoder (D) 28x28 MNIST digit images 200 dictionary elements Strokes for digit parts
16 Recognition Architecture C(x; K) Filterbank + Non-linearity + Pooling Linear classifier 64 filters Pinto 08
17 Recognition - C101 Optimal (Feature Sign, Lee 07) vs PSD features PSD features perform slightly better Naturally optimal point of sparsity After 64 features not much gain PSD features are hundreds of times faster
18 Redundancy in Feature Extraction Filters Convolve Feature maps Patch based learning has to model same structure at every location They produce highly redundant features
19 Convolutional PSD 1 2 mask(x) i D i z i z 1 + i z i C(k i x) 2 2 x R w h D R K s s z R K (w s+1) (h s+1) Patch based Convolutional Convolutional training yields a more diverse set of features
20 Convolutional PSD Measuring the redundancy in the dictionary Cumulative histogram of angle between every pair of dictionary elements 10 4 acos(abs(max(d i D T j ))) Patch Based Training Convolutional Training # of cross corr > deg deg
21 Convolutional PSD Encoder Training 2nd order information is important for fast convergence Better sparse representations can be obtained by using shrinkage operator Smooth shrinkage is important for conserving derivatives and parameters are learned 1 β log(exp(β b)+exp(β s) 1) b
22 Convolutional PSD Recognition Performance on C101 Low level convolutional feature learning improves significantly Patch Based SC Convolutional SC Unsup 52.2% 57.1% Unsup+ 54.2% 57.6% Unsup+ Unsupervised feature learning followed by supervised fine tuning
23 Multi-Stage Object Recognition Unsupervised Pre-Training Filter Bank Non- Linearity Pooling Unsupervised Pre-Training x z 1 Filter Bank Non- Linearity Pooling z 2 Supervised Refinement Filterbank - C(x;K) Non-linearities Pooling Building block of a multi-stage architecture
24 Recognition Accuracy on Caltech Patch Based Training 57.1 Unsupervised Unsupervised + Supervised 63.7 Convolutional Training 65.3 Unsupervised Stage 1 Stage 2 Stages 2 Stages Unsupervised + Supervised Unsupervised pre-training with Convolutional PSD yields better accuracy than patch-based PSD
25 Pedestrian Detection On INRIA Shapelet orig (90.5%) PoseInvSvm (68.6%) VJ OpenCv (53.0%) PoseInv (51.4%) Shapelet (50.4%) 0.3 VJ (47.5%) FtrMine (34.0%) miss rate % Pls (23.4%) HOG (23.1%) HikSvm (21.9%) LatSvm V1 (17.5%) MultiFtr (15.6%) R+R+ (14.8%) U+U+ (11.5%) 0.05 MultiFtr+CSS (10.9%) 11.5% LatSvm V2 (9.3%) FPDW (9.3%) ChnFtrs (8.7%) false positives per image Purely supervised training: 14.8% miss rate Unsupervised pre-training with Conv PSD + supervised refinement : 11.5% Close to state of the art and improving quickly...
26 Questions?
Learning Feature Hierarchies for Object Recognition
Learning Feature Hierarchies for Object Recognition Koray Kavukcuoglu Computer Science Department Courant Institute of Mathematical Sciences New York University Marc Aurelio Ranzato, Kevin Jarrett, Pierre
More informationLearning Convolutional Feature Hierarchies for Visual Recognition
Learning Convolutional Feature Hierarchies for Visual Recognition Koray Kavukcuoglu 1, Pierre Sermanet 1, Y-Lan Boureau 2,1, Karol Gregor 1, Michaël Mathieu 1, Yann LeCun 1 1 Courant Institute of Mathematical
More informationA 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 informationA 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 informationIntegral Channel Features Addendum
DOLLÁR, et al.: INTEGRAL CHANNEL FEATURES ADDENDUM 1 Integral Channel Features Addendum Piotr Dollár 1 pdollar@caltech.edu Zhuowen Tu 2 zhuowen.tu@loni.ucla.edu Pietro Perona 1 perona@caltech.edu Serge
More informationWhat is the Best Multi-Stage Architecture for Object Recognition?
What is the Best Multi-Stage Architecture for Object Recognition? Kevin Jarrett, Koray Kavukcuoglu, Marc Aurelio Ranzato and Yann LeCun The Courant Institute of Mathematical Sciences New York University,
More informationPedestrian Detection with Unsupervised Multi-Stage Feature Learning
2013 IEEE Conference on Computer Vision and Pattern Recognition Pedestrian Detection with Unsupervised Multi-Stage Feature Learning Pierre Sermanet Koray Kavukcuoglu Soumith Chintala Yann LeCun Courant
More informationCS229 Final Project Report. A Multi-Task Feature Learning Approach to Human Detection. Tiffany Low
CS229 Final Project Report A Multi-Task Feature Learning Approach to Human Detection Tiffany Low tlow@stanford.edu Abstract We focus on the task of human detection using unsupervised pre-trained neutral
More informationHierarchical Matching Pursuit for Image Classification: Architecture and Fast Algorithms
Hierarchical Matching Pursuit for Image Classification: Architecture and Fast Algorithms Liefeng Bo University of Washington Seattle WA 98195, USA Xiaofeng Ren ISTC-Pervasive Computing Intel Labs Seattle
More informationAdaptive Deconvolutional Networks for Mid and High Level Feature Learning
ICCV 2011 submission. Currently under review. Please do not distribute. Adaptive Deconvolutional Networks for Mid and High Level Feature Learning Matthew D. Zeiler, Graham W. Taylor and Rob Fergus Dept.
More informationUnsupervised Learning of Feature Hierarchies
Unsupervised Learning of Feature Hierarchies by Marc Aurelio Ranzato A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Department of Computer Science
More informationLearning Hierarchical Feature Extractors For Image Recognition
Learning Hierarchical Feature Extractors For Image Recognition by Y-Lan Boureau A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Department of
More informationLearning Hierarchical Feature Extractors For Image Recognition
Learning Hierarchical Feature Extractors For Image Recognition by Y-Lan Boureau A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Department of
More informationC. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun
Efficient Learning of Sparse Overcomplete Representations with an Energy-Based Model Marc'Aurelio Ranzato C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun CIAR Summer School Toronto 2006 Why Extracting
More informationLearning-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 informationSupplementary material for the paper Are Sparse Representations Really Relevant for Image Classification?
Supplementary material for the paper Are Sparse Representations Really Relevant for Image Classification? Roberto Rigamonti, Matthew A. Brown, Vincent Lepetit CVLab, EPFL Lausanne, Switzerland firstname.lastname@epfl.ch
More informationEfficient Algorithms may not be those we think
Efficient Algorithms may not be those we think Yann LeCun, Computational and Biological Learning Lab The Courant Institute of Mathematical Sciences New York University http://yann.lecun.com http://www.cs.nyu.edu/~yann
More informationSparse Models in Image Understanding And Computer Vision
Sparse Models in Image Understanding And Computer Vision Jayaraman J. Thiagarajan Arizona State University Collaborators Prof. Andreas Spanias Karthikeyan Natesan Ramamurthy Sparsity Sparsity of a vector
More informationGeneralized Lasso based Approximation of Sparse Coding for Visual Recognition
Generalized Lasso based Approximation of Sparse Coding for Visual Recognition Nobuyuki Morioka The University of New South Wales & NICTA Sydney, Australia nmorioka@cse.unsw.edu.au Shin ichi Satoh National
More informationBilevel Sparse Coding
Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional
More informationLEARNING A SPARSE DICTIONARY OF VIDEO STRUCTURE FOR ACTIVITY MODELING. Nandita M. Nayak, Amit K. Roy-Chowdhury. University of California, Riverside
LEARNING A SPARSE DICTIONARY OF VIDEO STRUCTURE FOR ACTIVITY MODELING Nandita M. Nayak, Amit K. Roy-Chowdhury University of California, Riverside ABSTRACT We present an approach which incorporates spatiotemporal
More informationHistograms of Sparse Codes for Object Detection
Histograms of Sparse Codes for Object Detection Xiaofeng Ren (Amazon), Deva Ramanan (UC Irvine) Presented by Hossein Azizpour What does the paper do? (learning) a new representation local histograms of
More informationarxiv: v1 [cs.lg] 20 Dec 2013
Unsupervised Feature Learning by Deep Sparse Coding Yunlong He Koray Kavukcuoglu Yun Wang Arthur Szlam Yanjun Qi arxiv:1312.5783v1 [cs.lg] 20 Dec 2013 Abstract In this paper, we propose a new unsupervised
More informationModeling Visual Cortex V4 in Naturalistic Conditions with Invari. Representations
Modeling Visual Cortex V4 in Naturalistic Conditions with Invariant and Sparse Image Representations Bin Yu Departments of Statistics and EECS University of California at Berkeley Rutgers University, May
More informationSemi-Supervised Hierarchical Models for 3D Human Pose Reconstruction
Semi-Supervised Hierarchical Models for 3D Human Pose Reconstruction Atul Kanaujia, CBIM, Rutgers Cristian Sminchisescu, TTI-C Dimitris Metaxas,CBIM, Rutgers 3D Human Pose Inference Difficulties Towards
More informationFacial Expression Classification with Random Filters Feature Extraction
Facial Expression Classification with Random Filters Feature Extraction Mengye Ren Facial Monkey mren@cs.toronto.edu Zhi Hao Luo It s Me lzh@cs.toronto.edu I. ABSTRACT In our work, we attempted to tackle
More informationUsing Machine Learning for Classification of Cancer Cells
Using Machine Learning for Classification of Cancer Cells Camille Biscarrat University of California, Berkeley I Introduction Cell screening is a commonly used technique in the development of new drugs.
More informationCPSC340. State-of-the-art Neural Networks. Nando de Freitas November, 2012 University of British Columbia
CPSC340 State-of-the-art Neural Networks Nando de Freitas November, 2012 University of British Columbia Outline of the lecture This lecture provides an overview of two state-of-the-art neural networks:
More informationCS 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 informationSupervised Translation-Invariant Sparse Coding
Supervised Translation-Invariant Sparse Coding Jianchao Yang,KaiYu, Thomas Huang Beckman Institute, University of Illinois at Urbana-Champaign NEC Laboratories America, Inc., Cupertino, California {jyang29,
More informationUnsupervised Learning of Spatiotemporally Coherent Metrics
Unsupervised Learning of Spatiotemporally Coherent Metrics Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun arxiv 2015. Presented by Jackie Chu Contributions Insight between slow feature
More informationA HMAX with LLC for Visual Recognition
A HMAX with LLC for Visual Recognition Kean Hong Lau, Yong Haur Tay, Fook Loong Lo Centre for Computing and Intelligent System Universiti Tunku Abdul Rahman, Kuala Lumpur, Malaysia {laukh,tayyh,lofl}@utar.edu.my
More informationJoint Deep Learning for Pedestrian Detection
Joint Deep Learning for Pedestrian Detection Wanli Ouyang and Xiaogang Wang Department of Electronic Engineering, the Chinese University of Hong Kong wlouyang, xgwang@ee.cuhk.edu.hk Abstract Feature extraction,
More informationComputer 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 informationConvolutional-Recursive Deep Learning for 3D Object Classification
Convolutional-Recursive Deep Learning for 3D Object Classification Richard Socher, Brody Huval, Bharath Bhat, Christopher D. Manning, Andrew Y. Ng NIPS 2012 Iro Armeni, Manik Dhar Motivation Hand-designed
More informationCOMP 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 informationComputer 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 informationDeep Learning for Generic Object Recognition
Deep Learning for Generic Object Recognition, Computational and Biological Learning Lab The Courant Institute of Mathematical Sciences New York University Collaborators: Marc'Aurelio Ranzato, Fu Jie Huang,
More informationThe Fastest Pedestrian Detector in the West
DOLLÁR, et al.: THE FASTEST PEDESTRIAN DETECTOR IN THE WEST The Fastest Pedestrian Detector in the West Piotr Dollár pdollar@caltech.edu Serge Belongie 2 sjb@cs.ucsd.edu Pietro Perona perona@caltech.edu
More informationarxiv: v1 [cs.cv] 4 Oct 2017
ENERGY-BASED SPHERICAL SPARSE CODING Bailey Kong and Charless C. Fowlkes Department of Computer Science University of California, Irvine Irvine, CA 92697 USA {bhkong,fowlkes}@ics.uci.edu ABSTRACT arxiv:1710.01820v1
More informationObject detection with CNNs
Object detection with CNNs 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before CNNs After CNNs 0% 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 year Region proposals
More informationObject detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation
Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN
More informationSparse coding for image classification
Sparse coding for image classification Columbia University Electrical Engineering: Kun Rong(kr2496@columbia.edu) Yongzhou Xiang(yx2211@columbia.edu) Yin Cui(yc2776@columbia.edu) Outline Background Introduction
More informationImage Restoration and Background Separation Using Sparse Representation Framework
Image Restoration and Background Separation Using Sparse Representation Framework Liu, Shikun Abstract In this paper, we introduce patch-based PCA denoising and k-svd dictionary learning method for the
More informationExtracting and Composing Robust Features with Denoising Autoencoders
Presenter: Alexander Truong March 16, 2017 Extracting and Composing Robust Features with Denoising Autoencoders Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol 1 Outline Introduction
More informationLearning 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 informationA New Algorithm for Training Sparse Autoencoders
A New Algorithm for Training Sparse Autoencoders Ali Shahin Shamsabadi, Massoud Babaie-Zadeh, Seyyede Zohreh Seyyedsalehi, Hamid R. Rabiee, Christian Jutten Sharif University of Technology, University
More informationLearning Fast Approximations of Sparse Coding
Karol Gregor and Yann LeCun {kgregor,yann}@cs.nyu.edu Courant Institute, New York University, 715 Broadway, New York, NY 10003, USA Abstract In Sparse Coding (SC), input vectors are reconstructed using
More informationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun Presented by Tushar Bansal Objective 1. Get bounding box for all objects
More informationarxiv: v2 [cs.lg] 22 Mar 2014
Alireza Makhzani makhzani@psi.utoronto.ca Brendan Frey frey@psi.utoronto.ca University of Toronto, 10 King s College Rd. Toronto, Ontario M5S 3G4, Canada arxiv:1312.5663v2 [cs.lg] 22 Mar 2014 Abstract
More informationDeveloping Open Source code for Pyramidal Histogram Feature Sets
Developing Open Source code for Pyramidal Histogram Feature Sets BTech Project Report by Subodh Misra subodhm@iitk.ac.in Y648 Guide: Prof. Amitabha Mukerjee Dept of Computer Science and Engineering IIT
More informationConvolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations
Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations Honglak Lee Roger Grosse Rajesh Ranganath Andrew Y. Ng Computer Science Department, Stanford University,
More informationLearning Algorithms for Medical Image Analysis. Matteo Santoro slipguru
Learning Algorithms for Medical Image Analysis Matteo Santoro slipguru santoro@disi.unige.it June 8, 2010 Outline 1. learning-based strategies for quantitative image analysis 2. automatic annotation of
More informationSparse Coding and Dictionary Learning for Image Analysis
Sparse Coding and Dictionary Learning for Image Analysis Part IV: Recent Advances in Computer Vision and New Models Francis Bach, Julien Mairal, Jean Ponce and Guillermo Sapiro CVPR 10 tutorial, San Francisco,
More informationStacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning Mohammad Norouzi, Mani Ranjbar, and Greg Mori School of Computing Science Simon Fraser University Burnaby, BC
More informationDeep 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 informationDeep 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 informationEfficient Learning of Sparse Representations with an Energy-Based Model
Efficient of Sparse Representations with an Energy-Based Model Marc Aurelio Ranzato, Christopher Poultney, Sumit Chopra, Yann Le Cun Presented by Pascal Lamblin February 14 th, 2007 Efficient of Sparse
More informationSparsity and image processing
Sparsity and image processing Aurélie Boisbunon INRIA-SAM, AYIN March 6, Why sparsity? Main advantages Dimensionality reduction Fast computation Better interpretability Image processing pattern recognition
More informationPedestrian Detection with Deep Convolutional Neural Network
Pedestrian Detection with Deep Convolutional Neural Network Xiaogang Chen, Pengxu Wei, Wei Ke, Qixiang Ye, Jianbin Jiao School of Electronic,Electrical and Communication Engineering, University of Chinese
More informationPedestrian Detection Based on Deep Convolutional Neural Network with Ensemble Inference Network
Pedestrian Detection Based on Deep Convolutional Neural Network with Ensemble Inference Network Hiroshi Fukui 1 Takayoshi Yamashita 1 Yui Yamauchi 1 Hironobu Fuiyoshi 1 Hiroshi Murase 2 Abstract Pedestrian
More informationGreedy algorithms for Sparse Dictionary Learning
Greedy algorithms for Sparse Dictionary Learning Varun Joshi 26 Apr 2017 Background. Sparse dictionary learning is a kind of representation learning where we express the data as a sparse linear combination
More informationSupplementary material: Efficient pedestrian detection by directly optimizing the partial area under the ROC curve
Supplementary material: Efficient pedestrian detection by directly optimizing the partial area under the ROC curve Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel The University of Adelaide,
More informationTA Section: Problem Set 4
TA Section: Problem Set 4 Outline Discriminative vs. Generative Classifiers Image representation and recognition models Bag of Words Model Part-based Model Constellation Model Pictorial Structures Model
More informationObject Classification Problem
HIERARCHICAL OBJECT CATEGORIZATION" Gregory Griffin and Pietro Perona. Learning and Using Taxonomies For Fast Visual Categorization. CVPR 2008 Marcin Marszalek and Cordelia Schmid. Constructing Category
More informationDiscriminative sparse model and dictionary learning for object category recognition
Discriative sparse model and dictionary learning for object category recognition Xiao Deng and Donghui Wang Institute of Artificial Intelligence, Zhejiang University Hangzhou, China, 31007 {yellowxiao,dhwang}@zju.edu.cn
More informationReconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling
Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling Michael Maire 1,2 Stella X. Yu 3 Pietro Perona 2 1 TTI Chicago 2 California Institute of Technology 3 University of California
More informationReturn of the Devil in the Details: Delving Deep into Convolutional Nets
Return of the Devil in the Details: Delving Deep into Convolutional Nets Ken Chatfield - Karen Simonyan - Andrea Vedaldi - Andrew Zisserman University of Oxford The Devil is still in the Details 2011 2014
More informationAn Exploration of Computer Vision Techniques for Bird Species Classification
An Exploration of Computer Vision Techniques for Bird Species Classification Anne L. Alter, Karen M. Wang December 15, 2017 Abstract Bird classification, a fine-grained categorization task, is a complex
More informationNovel Lossy Compression Algorithms with Stacked Autoencoders
Novel Lossy Compression Algorithms with Stacked Autoencoders Anand Atreya and Daniel O Shea {aatreya, djoshea}@stanford.edu 11 December 2009 1. Introduction 1.1. Lossy compression Lossy compression is
More informationDeep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks
Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin
More informationAn Analysis of Single-Layer Networks in Unsupervised Feature Learning
An Analysis of Single-Layer Networks in Unsupervised Feature Learning Adam Coates Honglak Lee Andrew Y. Ng Stanford University Computer Science Dept. 353 Serra Mall Stanford, CA 94305 University of Michigan
More informationComputer 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 informationEffective Auto Encoder For Unsupervised Sparse Representation
Wayne State University Wayne State University Theses 1-1-2015 Effective Auto Encoder For Unsupervised Sparse Representation Faria Mahnaz Wayne State University, Follow this and additional works at: http://digitalcommons.wayne.edu/oa_theses
More informationHuman Vision Based Object Recognition Sye-Min Christina Chan
Human Vision Based Object Recognition Sye-Min Christina Chan Abstract Serre, Wolf, and Poggio introduced an object recognition algorithm that simulates image processing in visual cortex and claimed to
More informationLightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction Rahaf Aljundi, Tinne Tuytelaars KU Leuven, ESAT-PSI - iminds, Belgium Abstract. Recently proposed domain adaptation methods
More informationMachine 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 informationMachine 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 informationA fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009]
A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation [Wen,Yin,Goldfarb,Zhang 2009] Yongjia Song University of Wisconsin-Madison April 22, 2010 Yongjia Song
More informationMultipath Sparse Coding Using Hierarchical Matching Pursuit
Multipath Sparse Coding Using Hierarchical Matching Pursuit Liefeng Bo, Xiaofeng Ren ISTC Pervasive Computing, Intel Labs Seattle WA 98195, USA {liefeng.bo,xiaofeng.ren}@intel.com Dieter Fox University
More informationLarge-Scale Visual Recognition With Deep Learning
Large-Scale Visual Recognition With Deep Learning Marc'Aurelio ranzato@google.com www.cs.toronto.edu/~ranzato Sunday 23 June 2013 Why Is Recognition Hard? Object Recognizer panda 2 Why Is Recognition Hard?
More informationDEEP 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 informationA Learned Dictionary Model for Texture Classification
Clara Fannjiang clarafj@stanford.edu. Abstract. Introduction Biological visual systems process incessant streams of natural images, and have done so since organisms first developed vision. To capture and
More informationUnsupervised Learning
Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy
More informationAlternatives to Direct Supervision
CreativeAI: Deep Learning for Graphics Alternatives to Direct Supervision Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TUM UCL Timetable Theory and Basics State of
More informationDeep 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 informationMultipath Sparse Coding Using Hierarchical Matching Pursuit
Multipath Sparse Coding Using Hierarchical Matching Pursuit Liefeng Bo ISTC-PC Intel Labs liefeng.bo@intel.com Xiaofeng Ren ISTC-PC Intel Labs xren@cs.washington.edu Dieter Fox University of Washington
More informationDeep 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 informationSupport Kernel Machines for Object Recognition
Support Kernel Machines for Object Recognition Ankita Kumar University of Pennsylvania Cristian Sminchisescu TTI-Chicago Abstract Kernel classifiers based on Support Vector Machines (SVM) have recently
More informationOn Compact Codes for Spatially Pooled Features
Yangqing Jia Oriol Vinyals Trevor Darrell UC Berkeley EECS, Berkeley, CA 97 USA jiayq@eecs.berkeley.edu vinyals@eecs.berkeley.edu trevor@eecs.berkeley.edu Abstract Feature encoding with an overcomplete
More informationA FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS. Kuan-Chuan Peng and Tsuhan Chen
A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS Kuan-Chuan Peng and Tsuhan Chen School of Electrical and Computer Engineering, Cornell University, Ithaca, NY
More informationWITH increasing penetration of portable multimedia. A Convolutional Neural Network Based Chinese Text Detection Algorithm via Text Structure Modeling
1 A Convolutional Neural Network Based Chinese Text Detection Algorithm via Text Structure Modeling Xiaohang Ren, Yi Zhou, Jianhua He, Senior Member, IEEE, Kai Chen Member, IEEE, Xiaokang Yang, Senior
More informationVisual Perception with Deep Learning
Visual Perception with Deep Learning Yann LeCun The Courant Institute of Mathematical Sciences New York University joint work with: Marc'Aurelio Ranzato, Y Lan Boureau, Koray Kavackuoglu, Fu Jie Huang,
More informationSparsity Based Regularization
9.520: Statistical Learning Theory and Applications March 8th, 200 Sparsity Based Regularization Lecturer: Lorenzo Rosasco Scribe: Ioannis Gkioulekas Introduction In previous lectures, we saw how regularization
More informationarxiv: v1 [cs.lg] 16 Nov 2010
DIPARTIMENTO DI INFORMATICA E SCIENZE DELL INFORMAZIONE arxiv:1011.3728v1 [cs.lg] 16 Nov 2010 PADDLE: Proximal Algorithm for Dual Dictionaries LEarning Curzio Basso, Matteo Santoro, Alessandro Verri, Silvia
More informationMachine Learning for Physicists Lecture 6. Summer 2017 University of Erlangen-Nuremberg Florian Marquardt
Machine Learning for Physicists Lecture 6 Summer 2017 University of Erlangen-Nuremberg Florian Marquardt Channels MxM image MxM image K K 3 channels conv 6 channels in any output channel, each pixel receives
More informationDeconvolution Networks
Deconvolution Networks Johan Brynolfsson Mathematical Statistics Centre for Mathematical Sciences Lund University December 6th 2016 1 / 27 Deconvolution Neural Networks 2 / 27 Image Deconvolution True
More informationECE 6504: Deep Learning for Perception
ECE 6504: Deep Learning for Perception Topics: (Finish) Backprop Convolutional Neural Nets Dhruv Batra Virginia Tech Administrativia Presentation Assignments https://docs.google.com/spreadsheets/d/ 1m76E4mC0wfRjc4HRBWFdAlXKPIzlEwfw1-u7rBw9TJ8/
More informationObject Category Detection. Slides mostly from Derek Hoiem
Object Category Detection Slides mostly from Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical template matching with sliding window Part-based Models
More informationLEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS
LEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS Alexey Dosovitskiy, Jost Tobias Springenberg and Thomas Brox University of Freiburg Presented by: Shreyansh Daftry Visual Learning and Recognition
More information