Return of the Devil in the Details: Delving Deep into Convolutional Nets

Size: px
Start display at page:

Download "Return of the Devil in the Details: Delving Deep into Convolutional Nets"

Transcription

1 Return of the Devil in the Details: Delving Deep into Convolutional Nets Ken Chatfield - Karen Simonyan - Andrea Vedaldi - Andrew Zisserman University of Oxford

2 The Devil is still in the Details

3 Comparing Apples to Apples: Back in 2011, state-of-the-art image classification pipelines were commonly based on the bag of visual words approach, with highly tuned feature encoders! State-of-the-art back in 2011!!! IFV LLC SV Improved Fisher Vector Locality Constrained Linear Coding Super-Vector Encoding! There were many feature encodings for this being proposed, but it was difficult to tell which worked best 3

4 Comparing Apples to Apples: State-of-the-art back in 2011 In our previous work (BMVC 2011) we conducted an extensive evaluation of these encodings comparing them all on a common-ground:! IFV! Input Dataset!! Fixed Feature Extractor LLC SV Fixed Learning Fixed Evaluation Protocol * we ll call the features from these encodings shallow to distinguish them from the CNN-based features which follow 4

5 What s Changed? State-of-the-art in 2014 Introduction of CNN-based deep visual features to the community, all using pre-trained networks (Krizhevsky et al. 2012, Donahue et al. 2013, Oquab et al. 2014, Sermanet et al. 2014) Have shown to perform excellently over standard classification and detection benchmarks Unclear how the different methods introduced recently compare to each other, and to shallow methods such as IFV 5

6 Comparing Apples to Apples: State-of-the-art in 2014 This work is again about comparing the latest methods on a common ground We compare both different pre-trained network architectures and different learning heuristics Input Dataset CNN Arch 1 CNN Arch 2 Fixed Learning Fixed Evaluation Protocol IFV 6

7 Performance Evolution over VOC map Our best CNN method achieves state-of-the-art performance over several datasets How do we get there? through comparison on equal footing, we determine what s important and what s not Method Dim. Aug. BOW 32K IFV-BL 327K IFV 84K IFV 84K f s DeCAF 4K t t CNN-F 4K f s CNN-M 2K 2K f s CNN-S 4K (TN) f s CNN-based methods 7

8 1 2 Augmentation Outline Study Introduction and Evaluation Setup Different pre-trained networks Data augmentation (for both CNN and IFV) Dataset fine-tuning Reducing CNN final layer output dimensionality Colour and CNN / IFV 8

9 Evaluation Setup Pre-trained Net on 1,000 ImageNet Classes training set test set CNN Feature Extractor (4096-D feature vector out) test train SVM Classifier classifier output Evaluate using map, accuracy etc. 9

10 1 Nets Pre-trained Networks CNN-F similar to Krizhevsky et al., NIPS 2012: ImageNet classification with deep convolutional networks! conv1! 64x11x11 stride 4 conv2! 256x5x5 stride 1 conv3! 256x3x3 stride 1 conv4! 256x3x3 conv5! 256x3x3 CNN-M similar to Zeiler and Fergus, CoRR 2013: Visualising and understanding convolutional networks fc6! 4096 d.o. fc7! 4096 drop-out! conv1! 96x7x7 stride 2 conv2! 256x5x5 stride 2 conv3! 512x3x3 stride 1 conv4! 512x3x3 conv5! 512x3x3 fc6! 4096 d.o. CNN-S similar to OverFeat accurate network, ICLR 2014: fc7! 4096 drop-out OverFeat: integrated recognition, localisation and detection using ConvNets' conv1! 96x7x7 stride 2 conv2! 256x5x5 stride 1 conv3! 512x3x3 stride 1 conv4! 512x3x3 conv5! 512x3x3 fc6! 4096 d.o. fc7! 4096 drop-out 10

11 1 Nets Pre-trained Networks map ( VOC07 ) Decaf CNN-F CNN-M CNN-S 11

12 1 2 Augmentation Outline Study Introduction and Evaluation Setup Different pre-trained networks Data augmentation (for both CNN and IFV) Dataset fine-tuning Reducing CNN final layer output dimensionality Colour and CNN / IFV 12

13 1 2 Augmentation Data Augmentation What do we mean by data augmentation? Network Pre-training (with jittering) Pre-trained Network CNN Feature Extractor a. Extract crops b. Pool features (average, max) 13

14 1 2 Augmentation Data Augmentation a. No augmentation (= 1 image) 224x224 b. Flip augmentation (= 2 images) 224x224 + c. Crop+Flip augmentation (= 10 images) 224x224 + flips 14

15 1 2 Augmentation Data Augmentation 80 None Flip Crop+Flip (train pooling: sum, test pooling: sum) Crop+Flip (train pooling: none, test pooling: sum) map ( VOC07 ) IFV CNN-M 15

16 1 2 3 Fine-tuning 4 5 Outline Study Introduction and Evaluation Setup Different pre-trained networks Data augmentation (for both CNN and IFV) Dataset fine-tuning Reducing CNN final layer output dimensionality Colour and CNN / IFV 16

17 1 2 3 Fine-tuning 4 5 Fine-tuning Network Pre-training images from ILSVRC-2012 Pre-trained Network General-purpose Features Network Fine-tuning images from target dataset Fine-tuned Network Dataset-specific Features For VOC 2007, the following loss functions were evaluated for the final fully connected layer: TN-CLS classification loss max{ 0, 1 - yw T φ( I ) } TN-RNK ranking loss max{ 0, 1 - w T ( φ( IPOS ) - φ( INEG ) ) } 17

18 1 2 3 Fine-tuning 4 5 Fine-tuning map ( VOC07 ) No TN CNN-S TN-RNK 18

19 Output Dim 5 Outline Study Introduction and Evaluation Setup Different pre-trained networks Data augmentation (for both CNN and IFV) Dataset fine-tuning Reducing CNN final layer output dimensionality Colour and CNN / IFV 19

20 Output Dim 5 Low Dimensional CNN Features Baseline networks all have 4096-D last hidden layer We further trained three modifications to CNN-M with lower dimensional full7 layers conv1! 96x7x7 st. 2 conv2! 256x5x5 st. 2, pad 1 conv3! 512x3x3 st. 1, pad 1 conv4! 512x3x3 conv5! 512x3x3 fc6! 4096 d.o. fc7! 4096 drop-out * Note: as only the original ILSVRC-2012 data was used for re-training this differs from fine-tuning and is simply a way of reducing the final output dimension

21 Output Dim 5 Low Dimensional CNN Features 81 map ( VOC07 ) CNN-M 21

22 IFV Exts. Outline Study Introduction and Evaluation Setup Different pre-trained networks Data augmentation (for both CNN and IFV) Dataset fine-tuning Reducing CNN final layer output dimensionality Colour and CNN / IFV 22

23 IFV Exts. Impact of Colour Greyscale Greyscale+aug Colour Colour+aug map ( VOC07 ) IFV-512 CNN-M 23

24 Comparison to State-of-the-art ILSVRC-2012 VOC2007 VOC2012 CNN-M CNN-S CNN-S TUNE-RNK Zeiler & Fergus Oquab et al. Oquab et al. Wei et al (82.8*) 86.3* 81.5 (85.2*) 81.7 (90.3*) * Uses extended training data and/or fusion with other methods 24

25 Take Home Messages CNN-based methods >> shallow methods We can transfer tricks from deep features to shallow features We can achieve incredibly low dimensional (~128-D) but performant features with CNN-based methods If you get the details right, it s possible to get to stateof-the-art with very simple methods 25

26 There s more Presented here was just a subset of the full results from the paper Check out the paper for full results on: VOC 2007 VOC 2012 Caltech-101 Caltech-256 ILSVRC

27 One more thing CNN models and feature computation code can now be downloaded from the project website: As before, source code to reproduce all experiments will be made available 27

28 Questions?

PASCAL VOC Classification: Local Features vs. Deep Features. Shuicheng YAN, NUS

PASCAL VOC Classification: Local Features vs. Deep Features. Shuicheng YAN, NUS PASCAL VOC Classification: Local Features vs. Deep Features Shuicheng YAN, NUS PASCAL VOC Why valuable? Multi-label, Real Scenarios! Visual Object Recognition Object Classification Object Detection Object

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

Two-Stream Convolutional Networks for Action Recognition in Videos

Two-Stream Convolutional Networks for Action Recognition in Videos Two-Stream Convolutional Networks for Action Recognition in Videos Karen Simonyan Andrew Zisserman Cemil Zalluhoğlu Introduction Aim Extend deep Convolution Networks to action recognition in video. Motivation

More information

Supplementary material for Analyzing Filters Toward Efficient ConvNet

Supplementary material for Analyzing Filters Toward Efficient ConvNet Supplementary material for Analyzing Filters Toward Efficient Net Takumi Kobayashi National Institute of Advanced Industrial Science and Technology, Japan takumi.kobayashi@aist.go.jp A. Orthonormal Steerable

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 Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos Tomas Pfister 1, Karen Simonyan 1, James Charles 2 and Andrew Zisserman 1 1 Visual Geometry Group, Department of Engineering

More information

WE are witnessing a rapid, revolutionary change in our

WE are witnessing a rapid, revolutionary change in our 1904 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 37, NO. 9, SEPTEMBER 2015 Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition Kaiming He, Xiangyu Zhang,

More information

Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation Rich feature hierarchies for accurate object detection and semantic segmentation Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik Presented by Pandian Raju and Jialin Wu Last class SGD for Document

More information

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

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

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

Intro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn

Intro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn Intro to Deep Learning Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn Why this class? Deep Features Have been able to harness the big data in the most efficient and effective

More information

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018 Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018 Outline: Introduction Action classification architectures

More information

Part Localization by Exploiting Deep Convolutional Networks

Part Localization by Exploiting Deep Convolutional Networks Part Localization by Exploiting Deep Convolutional Networks Marcel Simon, Erik Rodner, and Joachim Denzler Computer Vision Group, Friedrich Schiller University of Jena, Germany www.inf-cv.uni-jena.de Abstract.

More information

Large-scale Video Classification with Convolutional Neural Networks

Large-scale Video Classification with Convolutional Neural Networks Large-scale Video Classification with Convolutional Neural Networks Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-Fei Note: Slide content mostly from : Bay Area

More information

Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neural Networks

Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neural Networks Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neural Networks Nikiforos Pittaras 1, Foteini Markatopoulou 1,2, Vasileios Mezaris 1, and Ioannis Patras 2 1 Information Technologies

More information

Fuzzy Set Theory in Computer Vision: Example 3

Fuzzy Set Theory in Computer Vision: Example 3 Fuzzy Set Theory in Computer Vision: Example 3 Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Purpose of these slides are to make you aware of a few of the different CNN architectures

More information

arxiv: v1 [cs.cv] 4 Dec 2014

arxiv: v1 [cs.cv] 4 Dec 2014 Convolutional Neural Networks at Constrained Time Cost Kaiming He Jian Sun Microsoft Research {kahe,jiansun}@microsoft.com arxiv:1412.1710v1 [cs.cv] 4 Dec 2014 Abstract Though recent advanced convolutional

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

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

DeCAF: a Deep Convolutional Activation Feature for Generic Visual Recognition

DeCAF: a Deep Convolutional Activation Feature for Generic Visual Recognition DeCAF: a Deep Convolutional Activation Feature for Generic Visual Recognition ECS 289G 10/06/2016 Authors: Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng and Trevor Darrell

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

DD2427 Final Project Report. Human face attributes prediction with Deep Learning

DD2427 Final Project Report. Human face attributes prediction with Deep Learning DD2427 Final Project Report Human face attributes prediction with Deep Learning Abstract moaah@kth.se We explore using deep Convolutional Neural Networks (CNN) to predict human attributes like skin tune,

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

Tiny ImageNet Visual Recognition Challenge

Tiny ImageNet Visual Recognition Challenge Tiny ImageNet Visual Recognition Challenge Ya Le Department of Statistics Stanford University yle@stanford.edu Xuan Yang Department of Electrical Engineering Stanford University xuany@stanford.edu Abstract

More information

Bilinear Models for Fine-Grained Visual Recognition

Bilinear Models for Fine-Grained Visual Recognition Bilinear Models for Fine-Grained Visual Recognition Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst Fine-grained visual recognition Example: distinguish

More information

A 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 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 information

Using Machine Learning for Classification of Cancer Cells

Using 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 information

DEEP STRUCTURED OUTPUT LEARNING FOR UNCONSTRAINED TEXT RECOGNITION

DEEP STRUCTURED OUTPUT LEARNING FOR UNCONSTRAINED TEXT RECOGNITION DEEP STRUCTURED OUTPUT LEARNING FOR UNCONSTRAINED TEXT RECOGNITION Max Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman Visual Geometry Group, Department Engineering Science, University of Oxford,

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

Deep Learning for Computer Vision with MATLAB By Jon Cherrie

Deep Learning for Computer Vision with MATLAB By Jon Cherrie Deep Learning for Computer Vision with MATLAB By Jon Cherrie 2015 The MathWorks, Inc. 1 Deep learning is getting a lot of attention "Dahl and his colleagues won $22,000 with a deeplearning system. 'We

More information

Convolu'onal Neural Networks

Convolu'onal Neural Networks Convolu'onal Neural Networks Dr. Kira Radinsky CTO SalesPredict Visi8ng Professor/Scien8st Technion Slides were adapted from Fei-Fei Li & Andrej Karpathy & Jus8n Johnson A bit of history: Hubel & Wiesel,

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

Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab.

Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab. [ICIP 2017] Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab., POSTECH Pedestrian Detection Goal To draw bounding boxes that

More information

Convolutional Neural Networks

Convolutional Neural Networks NPFL114, Lecture 4 Convolutional Neural Networks Milan Straka March 25, 2019 Charles University in Prague Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics unless otherwise

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

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Kyunghee Kim Stanford University 353 Serra Mall Stanford, CA 94305 kyunghee.kim@stanford.edu Abstract We use a

More information

Regionlet Object Detector with Hand-crafted and CNN Feature

Regionlet Object Detector with Hand-crafted and CNN Feature Regionlet Object Detector with Hand-crafted and CNN Feature Xiaoyu Wang Research Xiaoyu Wang Research Ming Yang Horizon Robotics Shenghuo Zhu Alibaba Group Yuanqing Lin Baidu Overview of this section Regionlet

More information

Object detection with CNNs

Object 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 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

Final Report: Smart Trash Net: Waste Localization and Classification

Final Report: Smart Trash Net: Waste Localization and Classification Final Report: Smart Trash Net: Waste Localization and Classification Oluwasanya Awe oawe@stanford.edu Robel Mengistu robel@stanford.edu December 15, 2017 Vikram Sreedhar vsreed@stanford.edu Abstract Given

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

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

Robust Scene Classification with Cross-level LLC Coding on CNN Features

Robust Scene Classification with Cross-level LLC Coding on CNN Features Robust Scene Classification with Cross-level LLC Coding on CNN Features Zequn Jie 1, Shuicheng Yan 2 1 Keio-NUS CUTE Center, National University of Singapore, Singapore 2 Department of Electrical and Computer

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

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep 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 information

Pedestrian Detection with Deep Convolutional Neural Network

Pedestrian 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 information

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang, Pavlo Molchanov, Jan Kautz INTELLIGENT VIDEO ANALYTICS Surveillance event detection Human-computer interaction

More information

Lecture 37: ConvNets (Cont d) and Training

Lecture 37: ConvNets (Cont d) and Training Lecture 37: ConvNets (Cont d) and Training CS 4670/5670 Sean Bell [http://bbabenko.tumblr.com/post/83319141207/convolutional-learnings-things-i-learned-by] (Unrelated) Dog vs Food [Karen Zack, @teenybiscuit]

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

arxiv: v1 [cs.cv] 23 Apr 2015

arxiv: v1 [cs.cv] 23 Apr 2015 Object Detection Networks on Convolutional Feature Maps Shaoqing Ren Kaiming He Ross Girshick Xiangyu Zhang Jian Sun Microsoft Research {v-shren, kahe, rbg, v-xiangz, jiansun}@microsoft.com arxiv:1504.06066v1

More information

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery Remote Sens. 2015, 7, 14680-14707; doi:10.3390/rs71114680 OPEN ACCESS remote sensing ISSN 2072-4292 www.mdpi.com/journal/remotesensing Article Transferring Deep Convolutional Neural Networks for the Scene

More information

Project 3 Q&A. Jonathan Krause

Project 3 Q&A. Jonathan Krause Project 3 Q&A Jonathan Krause 1 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations 2 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations

More information

Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014

Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014 Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014 Problem Definition Viewpoint estimation: Given an image, predicting viewpoint for object of

More information

REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION

REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION Kingsley Kuan 1, Gaurav Manek 1, Jie Lin 1, Yuan Fang 1, Vijay Chandrasekhar 1,2 Institute for Infocomm Research, A*STAR, Singapore 1 Nanyang Technological

More information

Deep Residual Learning

Deep Residual Learning Deep Residual Learning MSRA @ ILSVRC & COCO 2015 competitions Kaiming He with Xiangyu Zhang, Shaoqing Ren, Jifeng Dai, & Jian Sun Microsoft Research Asia (MSRA) MSRA @ ILSVRC & COCO 2015 Competitions 1st

More information

Transfer Learning. Style Transfer in Deep Learning

Transfer Learning. Style Transfer in Deep Learning Transfer Learning & Style Transfer in Deep Learning 4-DEC-2016 Gal Barzilai, Ram Machlev Deep Learning Seminar School of Electrical Engineering Tel Aviv University Part 1: Transfer Learning in Deep Learning

More information

Object Detection Based on Deep Learning

Object Detection Based on Deep Learning Object Detection Based on Deep Learning Yurii Pashchenko AI Ukraine 2016, Kharkiv, 2016 Image classification (mostly what you ve seen) http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf

More information

arxiv: v2 [cs.cv] 26 Sep 2015

arxiv: v2 [cs.cv] 26 Sep 2015 AttentionNet: Aggregating Weak Directions for Accurate Object Detection Donggeun Yoo dgyoo@rcv.kaist.ac.kr KAIST Sunggyun Park sunggyun@kaist.ac.kr KAIST Joon-Young Lee jylee@rcv.kaist.ac.kr KAIST Anthony

More information

Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation Rich feature hierarchies for accurate object detection and semantic segmentation BY; ROSS GIRSHICK, JEFF DONAHUE, TREVOR DARRELL AND JITENDRA MALIK PRESENTER; MUHAMMAD OSAMA Object detection vs. classification

More information

arxiv: v2 [cs.cv] 19 Dec 2014

arxiv: v2 [cs.cv] 19 Dec 2014 Fisher Kernel for Deep Neural Activations Donggeun Yoo, Sunggyun Park, Joon-Young Lee, and In So Kweon arxiv:42.628v2 [cs.cv] 9 Dec 204 KAIST Daejeon, 305-70, Korea. dgyoo@rcv.kaist.ac.kr, sunggyun@kaist.ac.kr,

More information

Multiple VLAD encoding of CNNs for image classification

Multiple VLAD encoding of CNNs for image classification Multiple VLAD encoding of CNNs for image classification Qing Li, Qiang Peng, Chuan Yan 1 arxiv:1707.00058v1 [cs.cv] 30 Jun 2017 Abstract Despite the effectiveness of convolutional neural networks (CNNs)

More information

arxiv: v1 [cs.cv] 26 Jun 2017

arxiv: v1 [cs.cv] 26 Jun 2017 Detecting Small Signs from Large Images arxiv:1706.08574v1 [cs.cv] 26 Jun 2017 Zibo Meng, Xiaochuan Fan, Xin Chen, Min Chen and Yan Tong Computer Science and Engineering University of South Carolina, Columbia,

More information

arxiv: v1 [cs.cv] 18 Jun 2014

arxiv: v1 [cs.cv] 18 Jun 2014 Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition Technical report Kaiming He 1 Xiangyu Zhang 2 Shaoqing Ren 3 Jian Sun 1 1 Microsoft Research 2 Xi an Jiaotong University 3

More information

KamiNet A Convolutional Neural Network for Tiny ImageNet Challenge

KamiNet A Convolutional Neural Network for Tiny ImageNet Challenge KamiNet A Convolutional Neural Network for Tiny ImageNet Challenge Shaoming Feng Stanford University superfsm@stanford.edu Liang Shi Stanford University liangs@stanford.edu Abstract In this paper, we address

More information

Mixtures of Gaussians and Advanced Feature Encoding

Mixtures of Gaussians and Advanced Feature Encoding Mixtures of Gaussians and Advanced Feature Encoding Computer Vision Ali Borji UWM Many slides from James Hayes, Derek Hoiem, Florent Perronnin, and Hervé Why do good recognition systems go bad? E.g. Why

More information

Deep Spatial Pyramid Ensemble for Cultural Event Recognition

Deep Spatial Pyramid Ensemble for Cultural Event Recognition 215 IEEE International Conference on Computer Vision Workshops Deep Spatial Pyramid Ensemble for Cultural Event Recognition Xiu-Shen Wei Bin-Bin Gao Jianxin Wu National Key Laboratory for Novel Software

More information

Kaggle Data Science Bowl 2017 Technical Report

Kaggle Data Science Bowl 2017 Technical Report Kaggle Data Science Bowl 2017 Technical Report qfpxfd Team May 11, 2017 1 Team Members Table 1: Team members Name E-Mail University Jia Ding dingjia@pku.edu.cn Peking University, Beijing, China Aoxue Li

More information

MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection

MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection ILSVRC 2016 Object Detection from Video Byungjae Lee¹, Songguo Jin¹, Enkhbayar Erdenee¹, Mi Young Nam², Young Gui Jung², Phill Kyu

More information

A Deep Learning Framework for Authorship Classification of Paintings

A Deep Learning Framework for Authorship Classification of Paintings A Deep Learning Framework for Authorship Classification of Paintings Kai-Lung Hua ( 花凱龍 ) Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei,

More information

In Defense of Fully Connected Layers in Visual Representation Transfer

In Defense of Fully Connected Layers in Visual Representation Transfer In Defense of Fully Connected Layers in Visual Representation Transfer Chen-Lin Zhang, Jian-Hao Luo, Xiu-Shen Wei, Jianxin Wu National Key Laboratory for Novel Software Technology, Nanjing University,

More information

DeepIndex for Accurate and Efficient Image Retrieval

DeepIndex for Accurate and Efficient Image Retrieval DeepIndex for Accurate and Efficient Image Retrieval Yu Liu, Yanming Guo, Song Wu, Michael S. Lew Media Lab, Leiden Institute of Advance Computer Science Outline Motivation Proposed Approach Results Conclusions

More information

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity Constrained Local Enhancement of Semantic Features by Content-Based Sparsity Youssef Tamaazousti 12 Hervé Le Borgne 1 Adrian Popescu 1 1 CEA, LIST, Laboratory of Vision and Content Engineering, F-91191

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

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

Fully-Convolutional Siamese Networks for Object Tracking

Fully-Convolutional Siamese Networks for Object Tracking Fully-Convolutional Siamese Networks for Object Tracking Luca Bertinetto*, Jack Valmadre*, João Henriques, Andrea Vedaldi and Philip Torr www.robots.ox.ac.uk/~luca luca.bertinetto@eng.ox.ac.uk Tracking

More information

Semantic Segmentation

Semantic Segmentation Semantic Segmentation UCLA:https://goo.gl/images/I0VTi2 OUTLINE Semantic Segmentation Why? Paper to talk about: Fully Convolutional Networks for Semantic Segmentation. J. Long, E. Shelhamer, and T. Darrell,

More information

Yield Estimation using faster R-CNN

Yield Estimation using faster R-CNN Yield Estimation using faster R-CNN 1 Vidhya Sagar, 2 Sailesh J.Jain and 2 Arjun P. 1 Assistant Professor, 2 UG Scholar, Department of Computer Engineering and Science SRM Institute of Science and Technology,Chennai,

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

Content-Based Image Recovery

Content-Based Image Recovery Content-Based Image Recovery Hong-Yu Zhou and Jianxin Wu National Key Laboratory for Novel Software Technology Nanjing University, China zhouhy@lamda.nju.edu.cn wujx2001@nju.edu.cn Abstract. We propose

More information

Overall Description. Goal: to improve spatial invariance to the input data. Translation, Rotation, Scale, Clutter, Elastic

Overall Description. Goal: to improve spatial invariance to the input data. Translation, Rotation, Scale, Clutter, Elastic Philippe Giguère Overall Description Goal: to improve spatial invariance to the input data Translation, Rotation, Scale, Clutter, Elastic How: add a learnable module which explicitly manipulate spatially

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

arxiv: v3 [cs.cv] 13 Apr 2016 Abstract

arxiv: v3 [cs.cv] 13 Apr 2016 Abstract ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks Chen Sun 1,2 Manohar Paluri 2 Ronan Collobert 2 Ram Nevatia 1 Lubomir Bourdev 3 1 USC 2 Facebook AI Research 3 UC Berkeley

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

Exploit Bounding Box Annotations for Multi-label Object Recognition

Exploit Bounding Box Annotations for Multi-label Object Recognition Exploit Bounding Box Annotations for Multi-label Object Recognition Hao Yang 1, Joey Tianyi Zhou 2, Yu Zhang 3, Bin-Bin Gao 4, Jianxin Wu 4, and Jianfei Cai 1 1 SCE, Nanyang Technological University, lancelot365@gmail.com,

More information

Fast CNN-Based Object Tracking Using Localization Layers and Deep Features Interpolation

Fast CNN-Based Object Tracking Using Localization Layers and Deep Features Interpolation Fast CNN-Based Object Tracking Using Localization Layers and Deep Features Interpolation Al-Hussein A. El-Shafie Faculty of Engineering Cairo University Giza, Egypt elshafie_a@yahoo.com Mohamed Zaki Faculty

More information

arxiv: v1 [cs.cv] 9 Dec 2015

arxiv: v1 [cs.cv] 9 Dec 2015 Window-Object Relationship Guided Representation Learning for Generic Object Detections Xingyu ZENG Wanli OUYANG Xiaogang WANG The Chinese University of Hong Kong {xyzeng,wlouyang,xgwang}@ee.cuhk.edu.hk

More information

Convolution Neural Networks for Chinese Handwriting Recognition

Convolution Neural Networks for Chinese Handwriting Recognition Convolution Neural Networks for Chinese Handwriting Recognition Xu Chen Stanford University 450 Serra Mall, Stanford, CA 94305 xchen91@stanford.edu Abstract Convolutional neural networks have been proven

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

Deep Face Recognition. Nathan Sun

Deep Face Recognition. Nathan Sun Deep Face Recognition Nathan Sun Why Facial Recognition? Picture ID or video tracking Higher Security for Facial Recognition Software Immensely useful to police in tracking suspects Your face will be an

More information

Dense Image Labeling Using Deep Convolutional Neural Networks

Dense Image Labeling Using Deep Convolutional Neural Networks Dense Image Labeling Using Deep Convolutional Neural Networks Md Amirul Islam, Neil Bruce, Yang Wang Department of Computer Science University of Manitoba Winnipeg, MB {amirul, bruce, ywang}@cs.umanitoba.ca

More information

ConvolutionalNN's... ConvNet's... deep learnig

ConvolutionalNN's... ConvNet's... deep learnig Deep Learning ConvolutionalNN's... ConvNet's... deep learnig Markus Thaler, TG208 tham@zhaw.ch www.zhaw.ch/~tham Martin Weisenhorn, TB427 weie@zhaw.ch 20.08.2018 1 Neural Networks Classification: up to

More information

Deep learning for music, galaxies and plankton

Deep learning for music, galaxies and plankton Deep learning for music, galaxies and plankton Sander Dieleman May 17, 2016 1 I. Galaxies 2 http://www.galaxyzoo.org 3 4 The Galaxy Challenge: automate this classification process Competition on? model

More information

Efficient Convolutional Network Learning using Parametric Log based Dual-Tree Wavelet ScatterNet

Efficient Convolutional Network Learning using Parametric Log based Dual-Tree Wavelet ScatterNet Efficient Convolutional Network Learning using Parametric Log based Dual-Tree Wavelet ScatterNet Amarjot Singh, Nick Kingsbury Signal Processing Group, Department of Engineering, University of Cambridge,

More information

Fully-Convolutional Siamese Networks for Object Tracking

Fully-Convolutional Siamese Networks for Object Tracking Fully-Convolutional Siamese Networks for Object Tracking Luca Bertinetto*, Jack Valmadre*, João Henriques, Andrea Vedaldi and Philip Torr www.robots.ox.ac.uk/~luca luca.bertinetto@eng.ox.ac.uk Tracking

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

Paper Motivation. Fixed geometric structures of CNN models. CNNs are inherently limited to model geometric transformations

Paper Motivation. Fixed geometric structures of CNN models. CNNs are inherently limited to model geometric transformations Paper Motivation Fixed geometric structures of CNN models CNNs are inherently limited to model geometric transformations Higher-level features combine lower-level features at fixed positions as a weighted

More information

Rich feature hierarchies for accurate object detection and semant

Rich feature hierarchies for accurate object detection and semant Rich feature hierarchies for accurate object detection and semantic segmentation Speaker: Yucong Shen 4/5/2018 Develop of Object Detection 1 DPM (Deformable parts models) 2 R-CNN 3 Fast R-CNN 4 Faster

More information

Supplementary Material: Unconstrained Salient Object Detection via Proposal Subset Optimization

Supplementary Material: Unconstrained Salient Object Detection via Proposal Subset Optimization Supplementary Material: Unconstrained Salient Object via Proposal Subset Optimization 1. Proof of the Submodularity According to Eqns. 10-12 in our paper, the objective function of the proposed optimization

More information