Compacting ConvNets for end to end Learning

Size: px
Start display at page:

Download "Compacting ConvNets for end to end Learning"

Transcription

1 Compacting ConvNets for end to end Learning Jose M. Alvarez Joint work with Lars Pertersson, Hao Zhou, Fatih Porikli.

2 Success of CNN Image Classification Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, NIPS, 2012

3 Success of CNN Object Detection from Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arxiv:

4 Success of CNN Semantic Segmentation Jifeng Dai, Kaiming He, Jian Sun, BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation, arxiv:

5 Success of CNN Image Captioning Andrej Karpathy, Li Fei-Fei, Deep Visual-Semantic Alignments for Generating Image Description, CVPR, 2015 Video classification

6 Key of success Better training algorithms Batch normalization Initializations Momentum

7 Key of success Better training algorithms Large amount of data / labels

8 Key of success Better training algorithms Large amount of data / labels Hardware / Storage GPU, parallel systems Memory GPU (in Gb) GTX-580 Titan Black ('14) Titan X ('15)

9 Key of success Better training algorithms Large amount of data / labels Hardware / Storage Larger community of researchers

10 Key of success Enabled larger networks Num. Parameters (in Millions) LeNet-5 AlexNet VGGNet-16

11 Key of success 150 Num. Parameters (in Millions) LeNet-5 AlexNet VGGNet-16

12 Key of success 150 Num. Parameters (in Millions) LeNet-5 AlexNet VGGNet-16

13 Key of success 150 Num. Parameters (in Millions) LeNet-5 AlexNet VGGNet-16

14 Challenges Embedded devices with limited resources / power 2014 Jetson TK1 2015/16 Jetson TX1

15 Challenges Embedded devices with limited resources / power - Memory is a limiting factor - Real time operation

16 Computational Cost AlexNet Forward-pass is time consuming

17 Computational Cost AlexNet Memory bottleneck

18 Computational Cost VGGNet Memory bottleneck conv3-64 x 2 : 38,720 conv3-128 x 2 : 221,440 conv3-256 x 3 : 1,475,328 conv3-512 x 3 : 5,899,776 conv3-512 x 3 : 7,079,424 fc1 : 102,764,544 fc2 : 16,781,312 fc3 : 4,097,000 TOTAL : 138,357,544

19 Do we need all these parameters?

20 Over-Parameterization Needed for high non-convex optimization 1 Anna Choromanska, Mikael Henaff, Michael Mathieu, Gérard Ben Arous, Yann LeCun. The Loss Surfaces of Multilayer Networks

21 Over-Parameterization Needed for high non-convex optimization Deeper structures, larger learning capacity 1 1 Guido Montúfar, Razvan Pascanu, Kyunghyun Cho, Yoshua Bengio. On the Number of Linear Regions of Deep Neural Networks. NIPS 2014

22 Over-Parameterization Needed for high non-convex optimization Deeper structures, larger learning capacity From images to Video -> Even larger nets? A. Karpathy et. al. Large-scale Video Classification with Convolutional Neural Networks. CVPR 2014.

23 Compacting CNN

24 Compacting CNN Network distillation Network pruning Structured parameters Ours

25 Compacting CNN Network distillation

26 Compacting CNN Network distillation Large network learns from data Generate labels using the trained network Train smaller nets using the output or soft layer Geoffrey Hinton, Oriol Vinyals, Jeff Dean. Distilling the Knowledge in a Neural Network. NIPSw 2015

27 Compacting CNN Network distillation (II) Use intermediate layers to guide the training Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta and Yoshua Bengio. FitNets: Hints for Thin Deep Nets. ICLR 2015

28 Compacting CNN Pros In general better generalization and faster. Equal or slightly better performance Cons Requires a larger network to learn from.

29 Compacting CNN Network distillation Network pruning Directly remove unimportant parameters during training Requires second derivatives. Remove parameters + quantification 1 Good compression rates (orthogonal to other approaches) 1 S. Han, H. Mao, and W. J. Dally. Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, abs/ , 2015

30 Compacting CNN Network distillation Network pruning Structured parameters

31 Compacting CNN: Structured parameters Low rank approximations Max Jaderberg, Andrea Vedaldi, Andrew Zisserman Speeding up Convolutional Neural Networks with Low Rank Expansions. BMVC 2014

32 Compacting CNN: Structured parameters Low rank approximations (II) Emily Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus. Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation. NIPS 2014

33 Compacting CNN: Structured parameters Low rank approximations (III) Weights are approximated by a sum of rank 1 tensors. Emily Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus. Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation. NIPS 2014

34 Compacting CNN: Structured parameters Weak-Points Needs a full-rank network completely trained Not all filters can be approximated Theoretical speeds-up with drop of performance. Emily Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus. Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation. NIPS 2014

35 Compacting CNN: Structured parameters Weak-Points Needs a full-rank network completely trained. Not all filters can be approximated. Drop of performance. Strengths Potential ability to aid in regularization during or post training. Parameter sharing within the layer.

36 Compacting CNN: Structured parameters Low rank approximations (IV) VGG nets restrict filters during training. Same receptive field Deeper networks (more nonlinearities) Less parameters (49C 2 vs 3x(3x3)C 2 ) K. Simonyan, A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. ICLR, 2015

37 Compacting CNN: Structured parameters Low rank approximations (Ours 1 ) Filter restriction during training. Larger receptive fields Deeper networks (more nonlinearities) Parameter sharing Less parameters 1 Joint work with Lars Pertersson. Under review

38 Compacting CNN: Structured parameters Low rank approximations (Ours) ImageNet Results (AlexNet). Baseline: Alex Krizhevsky. Ilya Sutskever. Geoffrey Hinton. ImageNet Classification with Deep. Convolutional Neural Networks. NIPS 2012

39 Compacting CNN: Structured parameters Low rank approximations (Ours) Stereo Matching. Ours-3 32K Ours-1 32K Ours-1 48K Baseline: Jure Zbontar, Yann LeCun. Computing the Stereo Matching Cost With a Convolutional Neural Network. CVPR 2015

40 Memory?

41 Computational Cost VGGNet Memory bottleneck conv3-64 x 2 : 38,720 conv3-128 x 2 : 221,440 conv3-256 x 3 : 1,475,328 conv3-512 x 3 : 5,899,776 conv3-512 x 3 : 7,079,424 fc1 : 102,764,544 fc2 : 16,781,312 fc3 : 4,097,000 TOTAL : 138,357,544

42 Computational Cost AlexNet Memory bottleneck

43 Memory Bottleneck Sparse constraints during training (Ours 2 ) Directly reduce the number of neurons. Select the optimum number of neurons. Significant memory reductions with minor drop of performance 2 Joint work with Hao Zhou, Fatih Porikli. Under review

44 Memory Bottleneck Sparse constraints during training (Ours 2 ) 2 Joint work with Hao Zhou, Fatih Porikli. Under review

45 Do we need all these parameters?

46 Compacting ConvNets for end to end Learning Jose M. Alvarez Joint work with Lars Pertersson, Hao Zhou, Fatih Porikli.

Bert Huang Department of Computer Science Virginia Tech

Bert Huang Department of Computer Science Virginia Tech This paper was submitted as a final project report for CS6424/ECE6424 Probabilistic Graphical Models and Structured Prediction in the spring semester of 2016. The work presented here is done by students

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong Jan 26, 2016 Today Administrivia A bigger picture and some common questions Object detection proposals, by Samer

More information

Convolutional Feature Maps

Convolutional Feature Maps Convolutional Feature Maps Elements of efficient (and accurate) CNN-based object detection Kaiming He Microsoft Research Asia (MSRA) ICCV 2015 Tutorial on Tools for Efficient Object Detection Overview

More information

Pedestrian Detection with RCNN

Pedestrian Detection with RCNN Pedestrian Detection with RCNN Matthew Chen Department of Computer Science Stanford University mcc17@stanford.edu Abstract In this paper we evaluate the effectiveness of using a Region-based Convolutional

More information

Image and Video Understanding

Image and Video Understanding Image and Video Understanding 2VO 710.095 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

CS 1699: Intro to Computer Vision. Deep Learning. Prof. Adriana Kovashka University of Pittsburgh December 1, 2015

CS 1699: Intro to Computer Vision. Deep Learning. Prof. Adriana Kovashka University of Pittsburgh December 1, 2015 CS 1699: Intro to Computer Vision Deep Learning Prof. Adriana Kovashka University of Pittsburgh December 1, 2015 Today: Deep neural networks Background Architectures and basic operations Applications Visualizing

More information

Module 5. Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016

Module 5. Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016 Module 5 Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016 Previously, end-to-end.. Dog Slide credit: Jose M 2 Previously, end-to-end.. Dog Learned Representation Slide credit: Jose

More information

Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg

Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Introduction http://stevenhoi.org/ Finance Recommender Systems Cyber Security Machine Learning Visual

More information

Network Morphism. Abstract. 1. Introduction. Tao Wei

Network Morphism. Abstract. 1. Introduction. Tao Wei Tao Wei TAOWEI@BUFFALO.EDU Changhu Wang CHW@MICROSOFT.COM Yong Rui YONGRUI@MICROSOFT.COM Chang Wen Chen CHENCW@BUFFALO.EDU Microsoft Research, Beijing, China, 18 Department of Computer Science and Engineering,

More information

Fast R-CNN Object detection with Caffe

Fast R-CNN Object detection with Caffe Fast R-CNN Object detection with Caffe Ross Girshick Microsoft Research arxiv code Latest roasts Goals for this section Super quick intro to object detection Show one way to tackle obj. det. with ConvNets

More information

Object Detection in Video using Faster R-CNN

Object Detection in Video using Faster R-CNN Object Detection in Video using Faster R-CNN Prajit Ramachandran University of Illinois at Urbana-Champaign prmchnd2@illinois.edu Abstract Convolutional neural networks (CNN) currently dominate the computer

More information

CNN Based Object Detection in Large Video Images. WangTao, wtao@qiyi.com IQIYI ltd. 2016.4

CNN Based Object Detection in Large Video Images. WangTao, wtao@qiyi.com IQIYI ltd. 2016.4 CNN Based Object Detection in Large Video Images WangTao, wtao@qiyi.com IQIYI ltd. 2016.4 Outline Introduction Background Challenge Our approach System framework Object detection Scene recognition Body

More information

MulticoreWare. Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan

MulticoreWare. Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan 1 MulticoreWare Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan Focused on Heterogeneous Computing Multiple verticals spawned from core competency Machine Learning

More information

Pedestrian Detection using R-CNN

Pedestrian Detection using R-CNN Pedestrian Detection using R-CNN CS676A: Computer Vision Project Report Advisor: Prof. Vinay P. Namboodiri Deepak Kumar Mohit Singh Solanki (12228) (12419) Group-17 April 15, 2016 Abstract Pedestrian detection

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 Deep Learning Barnabás Póczos & Aarti Singh Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio Geoffrey

More information

Image Classification for Dogs and Cats

Image Classification for Dogs and Cats Image Classification for Dogs and Cats Bang Liu, Yan Liu Department of Electrical and Computer Engineering {bang3,yan10}@ualberta.ca Kai Zhou Department of Computing Science kzhou3@ualberta.ca Abstract

More information

Fast R-CNN. Author: Ross Girshick Speaker: Charlie Liu Date: Oct, 13 th. Girshick, R. (2015). Fast R-CNN. arxiv preprint arxiv:1504.08083.

Fast R-CNN. Author: Ross Girshick Speaker: Charlie Liu Date: Oct, 13 th. Girshick, R. (2015). Fast R-CNN. arxiv preprint arxiv:1504.08083. Fast R-CNN Author: Ross Girshick Speaker: Charlie Liu Date: Oct, 13 th Girshick, R. (2015). Fast R-CNN. arxiv preprint arxiv:1504.08083. ECS 289G 001 Paper Presentation, Prof. Lee Result 1 67% Accuracy

More information

Deformable Part Models with CNN Features

Deformable Part Models with CNN Features Deformable Part Models with CNN Features Pierre-André Savalle 1, Stavros Tsogkas 1,2, George Papandreou 3, Iasonas Kokkinos 1,2 1 Ecole Centrale Paris, 2 INRIA, 3 TTI-Chicago Abstract. In this work we

More information

arxiv:1409.1556v6 [cs.cv] 10 Apr 2015

arxiv:1409.1556v6 [cs.cv] 10 Apr 2015 VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION Karen Simonyan & Andrew Zisserman + Visual Geometry Group, Department of Engineering Science, University of Oxford {karen,az}@robots.ox.ac.uk

More information

Lecture 6: Classification & Localization. boris. ginzburg@intel.com

Lecture 6: Classification & Localization. boris. ginzburg@intel.com Lecture 6: Classification & Localization boris. ginzburg@intel.com 1 Agenda ILSVRC 2014 Overfeat: integrated classification, localization, and detection Classification with Localization Detection. 2 ILSVRC-2014

More information

GPU-Based Deep Learning Inference:

GPU-Based Deep Learning Inference: Whitepaper GPU-Based Deep Learning Inference: A Performance and Power Analysis November 2015 1 Contents Abstract... 3 Introduction... 3 Inference versus Training... 4 GPUs Excel at Neural Network Inference...

More information

Administrivia. Traditional Recognition Approach. Overview. CMPSCI 370: Intro. to Computer Vision Deep learning

Administrivia. Traditional Recognition Approach. Overview. CMPSCI 370: Intro. to Computer Vision Deep learning : Intro. to Computer Vision Deep learning University of Massachusetts, Amherst April 19/21, 2016 Instructor: Subhransu Maji Finals (everyone) Thursday, May 5, 1-3pm, Hasbrouck 113 Final exam Tuesday, May

More information

Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks

Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks 1 Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks Tomislav Hrkać, Karla Brkić, Zoran Kalafatić Faculty of Electrical Engineering and Computing University of

More information

Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection

Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection CSED703R: Deep Learning for Visual Recognition (206S) Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 3 Object detection

More information

arxiv:1312.6034v2 [cs.cv] 19 Apr 2014

arxiv:1312.6034v2 [cs.cv] 19 Apr 2014 Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps arxiv:1312.6034v2 [cs.cv] 19 Apr 2014 Karen Simonyan Andrea Vedaldi Andrew Zisserman Visual Geometry Group,

More information

arxiv:1506.03365v2 [cs.cv] 19 Jun 2015

arxiv:1506.03365v2 [cs.cv] 19 Jun 2015 LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop Fisher Yu Yinda Zhang Shuran Song Ari Seff Jianxiong Xiao arxiv:1506.03365v2 [cs.cv] 19 Jun 2015 Princeton

More information

Deep Residual Networks

Deep Residual Networks Deep Residual Networks Deep Learning Gets Way Deeper 8:30-10:30am, June 19 ICML 2016 tutorial Kaiming He Facebook AI Research* *as of July 2016. Formerly affiliated with Microsoft Research Asia 7x7 conv,

More information

arxiv:1604.08893v1 [cs.cv] 29 Apr 2016

arxiv:1604.08893v1 [cs.cv] 29 Apr 2016 Faster R-CNN Features for Instance Search Amaia Salvador, Xavier Giró-i-Nieto, Ferran Marqués Universitat Politècnica de Catalunya (UPC) Barcelona, Spain {amaia.salvador,xavier.giro}@upc.edu Shin ichi

More information

An Introduction to Deep Learning

An Introduction to Deep Learning Thought Leadership Paper Predictive Analytics An Introduction to Deep Learning Examining the Advantages of Hierarchical Learning Table of Contents 4 The Emergence of Deep Learning 7 Applying Deep-Learning

More information

Getting Started with Caffe Julien Demouth, Senior Engineer

Getting Started with Caffe Julien Demouth, Senior Engineer Getting Started with Caffe Julien Demouth, Senior Engineer What is Caffe? Open Source Framework for Deep Learning http://github.com/bvlc/caffe Developed by the Berkeley Vision and Learning Center (BVLC)

More information

arxiv:1412.6856v2 [cs.cv] 15 Apr 2015

arxiv:1412.6856v2 [cs.cv] 15 Apr 2015 Published as a conference paper at ICLR 215 OBJECT DETECTORS EMERGE IN DEEP SCENE CNNS Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Computer Science and Artificial Intelligence

More information

Fast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN

Fast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN Fast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN Xiu Li 1, 2, Min Shang 1, 2, Hongwei Qin 1, 2, Liansheng Chen 1, 2 1. Department of Automation, Tsinghua University, Beijing

More information

Image Caption Generator Based On Deep Neural Networks

Image Caption Generator Based On Deep Neural Networks Image Caption Generator Based On Deep Neural Networks Jianhui Chen CPSC 503 CS Department Wenqiang Dong CPSC 503 CS Department Minchen Li CPSC 540 CS Department Abstract In this project, we systematically

More information

Learning and transferring mid-level image representions using convolutional neural networks

Learning and transferring mid-level image representions using convolutional neural networks Willow project-team Learning and transferring mid-level image representions using convolutional neural networks Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic 1 Image classification (easy) Is there

More information

Learning to Process Natural Language in Big Data Environment

Learning to Process Natural Language in Big Data Environment CCF ADL 2015 Nanchang Oct 11, 2015 Learning to Process Natural Language in Big Data Environment Hang Li Noah s Ark Lab Huawei Technologies Part 1: Deep Learning - Present and Future Talk Outline Overview

More information

arxiv:1502.01852v1 [cs.cv] 6 Feb 2015

arxiv:1502.01852v1 [cs.cv] 6 Feb 2015 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun arxiv:1502.01852v1 [cs.cv] 6 Feb 2015 Abstract Rectified activation

More information

Bayesian Dark Knowledge

Bayesian Dark Knowledge Bayesian Dark Knowledge Anoop Korattikara, Vivek Rathod, Kevin Murphy Google Research {kbanoop, rathodv, kpmurphy}@google.com Max Welling University of Amsterdam m.welling@uva.nl Abstract We consider the

More information

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers Fan Yang 1,2, Wongun Choi 2, and Yuanqing Lin 2 1 Department of Computer Science,

More information

arxiv:1504.08083v2 [cs.cv] 27 Sep 2015

arxiv:1504.08083v2 [cs.cv] 27 Sep 2015 Fast R-CNN Ross Girshick Microsoft Research rbg@microsoft.com arxiv:1504.08083v2 [cs.cv] 27 Sep 2015 Abstract This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object

More information

Taking Inverse Graphics Seriously

Taking Inverse Graphics Seriously CSC2535: 2013 Advanced Machine Learning Taking Inverse Graphics Seriously Geoffrey Hinton Department of Computer Science University of Toronto The representation used by the neural nets that work best

More information

Deep Learning and GPUs. Julie Bernauer

Deep Learning and GPUs. Julie Bernauer Deep Learning and GPUs Julie Bernauer GPU Computing 2 GPU Computing x86 3 CUDA Framework to Program NVIDIA GPUs A simple sum of two vectors (arrays) in C void vector_add(int n, const float *a, const float

More information

SIGNAL INTERPRETATION

SIGNAL INTERPRETATION SIGNAL INTERPRETATION Lecture 6: ConvNets February 11, 2016 Heikki Huttunen heikki.huttunen@tut.fi Department of Signal Processing Tampere University of Technology CONVNETS Continued from previous slideset

More information

Simultaneous Deep Transfer Across Domains and Tasks

Simultaneous Deep Transfer Across Domains and Tasks Simultaneous Deep Transfer Across Domains and Tasks Eric Tzeng, Judy Hoffman, Trevor Darrell UC Berkeley, EECS & ICSI {etzeng,jhoffman,trevor}@eecs.berkeley.edu Kate Saenko UMass Lowell, CS saenko@cs.uml.edu

More information

Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity

Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity Eri Matsuo Ichiro Kobayashi Ochanomizu University g1220535@is.ocha.ac.jp koba@is.ocha.ac.jp Shinji Nishimoto

More information

This is the author s version of a work that was submitted/accepted for publication in the following source:

This is the author s version of a work that was submitted/accepted for publication in the following source: This is the author s version of a work that was submitted/accepted for publication in the following source: Bewley, Alex & Upcroft, Ben (2015) From ImageNet to mining: Adapting visual object detection

More information

Applications of Deep Learning to the GEOINT mission. June 2015

Applications of Deep Learning to the GEOINT mission. June 2015 Applications of Deep Learning to the GEOINT mission June 2015 Overview Motivation Deep Learning Recap GEOINT applications: Imagery exploitation OSINT exploitation Geospatial and activity based analytics

More information

Convolutional Neural Networks with Intra-layer Recurrent Connections for Scene Labeling

Convolutional Neural Networks with Intra-layer Recurrent Connections for Scene Labeling Convolutional Neural Networks with Intra-layer Recurrent Connections for Scene Labeling Ming Liang Xiaolin Hu Bo Zhang Tsinghua National Laboratory for Information Science and Technology (TNList) Department

More information

Deep Learning for Big Data

Deep Learning for Big Data Deep Learning for Big Data Yoshua Bengio Département d Informa0que et Recherche Opéra0onnelle, U. Montréal 30 May 2013, Journée de la recherche École Polytechnique, Montréal Big Data & Data Science Super-

More information

Do Convnets Learn Correspondence?

Do Convnets Learn Correspondence? Do Convnets Learn Correspondence? Jonathan Long Ning Zhang Trevor Darrell University of California Berkeley {jonlong, nzhang, trevor}@cs.berkeley.edu Abstract Convolutional neural nets (convnets) trained

More information

PhD in Computer Science and Engineering Bologna, April 2016. Machine Learning. Marco Lippi. marco.lippi3@unibo.it. Marco Lippi Machine Learning 1 / 80

PhD in Computer Science and Engineering Bologna, April 2016. Machine Learning. Marco Lippi. marco.lippi3@unibo.it. Marco Lippi Machine Learning 1 / 80 PhD in Computer Science and Engineering Bologna, April 2016 Machine Learning Marco Lippi marco.lippi3@unibo.it Marco Lippi Machine Learning 1 / 80 Recurrent Neural Networks Marco Lippi Machine Learning

More information

Deep Learning & Convolutional Networks

Deep Learning & Convolutional Networks Deep Learning & Convolutional Networks Yann LeCun Facebook AI Research & Center for Data Science, NYU yann@cs.nyu.edu http://yann.lecun.com Machine Learning (Supervised Lerning) training a machine to distinguish

More information

Understanding Deep Image Representations by Inverting Them

Understanding Deep Image Representations by Inverting Them Understanding Deep Image Representations by Inverting Them Aravindh Mahendran University of Oxford aravindh@robots.ox.ac.uk Andrea Vedaldi University of Oxford vedaldi@robots.ox.ac.uk Abstract Image representations,

More information

3D Object Recognition using Convolutional Neural Networks with Transfer Learning between Input Channels

3D Object Recognition using Convolutional Neural Networks with Transfer Learning between Input Channels 3D Object Recognition using Convolutional Neural Networks with Transfer Learning between Input Channels Luís A. Alexandre Department of Informatics and Instituto de Telecomunicações Univ. Beira Interior,

More information

arxiv:1502.03044v3 [cs.lg] 19 Apr 2016

arxiv:1502.03044v3 [cs.lg] 19 Apr 2016 Show, ttend and Tell: Neural Image Caption Generation with Visual ttention arxiv:1502.03044v3 [cs.lg] 19 pr 2016 Kelvin Xu Jimmy Lei Ba Ryan Kiros Kyunghyun Cho aron Courville Ruslan Salakhutdinov Richard

More information

InstaNet: Object Classification Applied to Instagram Image Streams

InstaNet: Object Classification Applied to Instagram Image Streams InstaNet: Object Classification Applied to Instagram Image Streams Clifford Huang Stanford University chuang8@stanford.edu Mikhail Sushkov Stanford University msushkov@stanford.edu Abstract The growing

More information

On the Number of Linear Regions of Deep Neural Networks

On the Number of Linear Regions of Deep Neural Networks On the Number of Linear Regions of Deep Neural Networks Guido Montúfar Max Planck Institute for Mathematics in the Sciences montufar@mis.mpg.de Razvan Pascanu Université de Montréal pascanur@iro.umontreal.ca

More information

arxiv:1405.3866v1 [cs.cv] 15 May 2014

arxiv:1405.3866v1 [cs.cv] 15 May 2014 JADERBERG, VEDALDI, AND ZISSERMAN: SPEEDING UP CONVOLUTIONAL... 1 arxiv:1405.3866v1 [cs.cv] 15 May 014 Speeding up Convolutional Neural Networks with Low Rank Expansions Max Jaderberg max@robots.ox.ac.uk

More information

HE Shuncheng hsc12@outlook.com. March 20, 2016

HE Shuncheng hsc12@outlook.com. March 20, 2016 Department of Automation Association of Science and Technology of Automation March 20, 2016 Contents Binary Figure 1: a cat? Figure 2: a dog? Binary : Given input data x (e.g. a picture), the output of

More information

SEMANTIC CONTEXT AND DEPTH-AWARE OBJECT PROPOSAL GENERATION

SEMANTIC CONTEXT AND DEPTH-AWARE OBJECT PROPOSAL GENERATION SEMANTIC TEXT AND DEPTH-AWARE OBJECT PROPOSAL GENERATION Haoyang Zhang,, Xuming He,, Fatih Porikli,, Laurent Kneip NICTA, Canberra; Australian National University, Canberra ABSTRACT This paper presents

More information

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 69 Class Project Report Junhua Mao and Lunbo Xu University of California, Los Angeles mjhustc@ucla.edu and lunbo

More information

Big Data in the Mathematical Sciences

Big Data in the Mathematical Sciences Big Data in the Mathematical Sciences Wednesday 13 November 2013 Sponsored by: Extract from Campus Map Note: Walk from Zeeman Building to Arts Centre approximately 5 minutes ZeemanBuilding BuildingNumber38

More information

Deep Learning using Linear Support Vector Machines

Deep Learning using Linear Support Vector Machines Yichuan Tang tang@cs.toronto.edu Department of Computer Science, University of Toronto. Toronto, Ontario, Canada. Abstract Recently, fully-connected and convolutional neural networks have been trained

More information

arxiv:1505.04597v1 [cs.cv] 18 May 2015

arxiv:1505.04597v1 [cs.cv] 18 May 2015 U-Net: Convolutional Networks for Biomedical Image Segmentation Olaf Ronneberger, Philipp Fischer, and Thomas Brox arxiv:1505.04597v1 [cs.cv] 18 May 2015 Computer Science Department and BIOSS Centre for

More information

Deep Image: Scaling up Image Recognition

Deep Image: Scaling up Image Recognition Deep Image: Scaling up Image Recognition Ren Wu 1, Shengen Yan, Yi Shan, Qingqing Dang, Gang Sun Baidu Research Abstract We present a state-of-the-art image recognition system, Deep Image, developed using

More information

Marr Revisited: 2D-3D Alignment via Surface Normal Prediction

Marr Revisited: 2D-3D Alignment via Surface Normal Prediction Marr Revisited: 2D-3D Alignment via Surface Normal Prediction Aayush Bansal Bryan Russell2 Abhinav Gupta Carnegie Mellon University 2 Adobe Research http://www.cs.cmu.edu/ aayushb/marrrevisited/ Input&Image&

More information

R-CNN minus R. 1 Introduction. Karel Lenc http://www.robots.ox.ac.uk/~karel. Department of Engineering Science, University of Oxford, Oxford, UK.

R-CNN minus R. 1 Introduction. Karel Lenc http://www.robots.ox.ac.uk/~karel. Department of Engineering Science, University of Oxford, Oxford, UK. LENC, VEDALDI: R-CNN MINUS R 1 R-CNN minus R Karel Lenc http://www.robots.ox.ac.uk/~karel Andrea Vedaldi http://www.robots.ox.ac.uk/~vedaldi Department of Engineering Science, University of Oxford, Oxford,

More information

Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15

Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15 Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15 GENIVI is a registered trademark of the GENIVI Alliance in the USA and other countries Copyright GENIVI Alliance

More information

Storing and Analyzing Efficiently Big Data at GSI/FAIR

Storing and Analyzing Efficiently Big Data at GSI/FAIR Storing and Analyzing Efficiently Big Data at GSI/FAIR Thomas Stibor GSI Helmholtz Centre for Heavy Ion Research, HPC 8. Mai 2014 Overview GSI/FAIR p-linac SIS100/300 UNILAC SIS18 CBM HESR PANDA Rare Isotope

More information

Implementation of Neural Networks with Theano. http://deeplearning.net/tutorial/

Implementation of Neural Networks with Theano. http://deeplearning.net/tutorial/ Implementation of Neural Networks with Theano http://deeplearning.net/tutorial/ Feed Forward Neural Network (MLP) Hidden Layer Object Hidden Layer Object Hidden Layer Object Logistic Regression Object

More information

Sense Making in an IOT World: Sensor Data Analysis with Deep Learning

Sense Making in an IOT World: Sensor Data Analysis with Deep Learning Sense Making in an IOT World: Sensor Data Analysis with Deep Learning Natalia Vassilieva, PhD Senior Research Manager GTC 2016 Deep learning proof points as of today Vision Speech Text Other Search & information

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 Visual Geometry Group, University of Oxford {karen,az}@robots.ox.ac.uk Abstract We investigate architectures

More information

arxiv:1412.1897v4 [cs.cv] 2 Apr 2015

arxiv:1412.1897v4 [cs.cv] 2 Apr 2015 Full Citation: Nguyen A, Yosinski J, Clune J. Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images. In Computer Vision and Pattern Recognition (CVPR 15), IEEE,

More information

Object Detection from Video Tubelets with Convolutional Neural Networks

Object Detection from Video Tubelets with Convolutional Neural Networks Object Detection from Video Tubelets with Convolutional Neural Networks Kai Kang Wanli Ouyang Hongsheng Li Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong {kkang,wlouyang,hsli,xgwang}@ee.cuhk.edu.hk

More information

Interactive Level-Set Deformation On the GPU

Interactive Level-Set Deformation On the GPU Interactive Level-Set Deformation On the GPU Institute for Data Analysis and Visualization University of California, Davis Problem Statement Goal Interactive system for deformable surface manipulation

More information

A Bayesian Framework for Unsupervised One-Shot Learning of Object Categories

A Bayesian Framework for Unsupervised One-Shot Learning of Object Categories A Bayesian Framework for Unsupervised One-Shot Learning of Object Categories Li Fei-Fei 1 Rob Fergus 1,2 Pietro Perona 1 1. California Institute of Technology 2. Oxford University Single Object Object

More information

Stochastic Pooling for Regularization of Deep Convolutional Neural Networks

Stochastic Pooling for Regularization of Deep Convolutional Neural Networks Stochastic Pooling for Regularization of Deep Convolutional Neural Networks Matthew D. Zeiler Department of Computer Science Courant Institute, New York University zeiler@cs.nyu.edu Rob Fergus Department

More information

Advanced analytics at your hands

Advanced analytics at your hands 2.3 Advanced analytics at your hands Neural Designer is the most powerful predictive analytics software. It uses innovative neural networks techniques to provide data scientists with results in a way previously

More information

Scalable Machine Learning - or what to do with all that Big Data infrastructure

Scalable Machine Learning - or what to do with all that Big Data infrastructure - or what to do with all that Big Data infrastructure TU Berlin blog.mikiobraun.de Strata+Hadoop World London, 2015 1 Complex Data Analysis at Scale Click-through prediction Personalized Spam Detection

More information

Multi-view Face Detection Using Deep Convolutional Neural Networks

Multi-view Face Detection Using Deep Convolutional Neural Networks Multi-view Face Detection Using Deep Convolutional Neural Networks Sachin Sudhakar Farfade Yahoo fsachin@yahoo-inc.com Mohammad Saberian Yahoo saberian@yahooinc.com Li-Jia Li Yahoo lijiali@cs.stanford.edu

More information

Taking a Deeper Look at Pedestrians

Taking a Deeper Look at Pedestrians Taking a Deeper Look at Pedestrians Jan Hosang Mohamed Omran Rodrigo Benenson Bernt Schiele Max Planck Institute for Informatics Saarbrücken, Germany firstname.lastname@mpi-inf.mpg.de Abstract In this

More information

DEEP LEARNING WITH GPUS

DEEP LEARNING WITH GPUS DEEP LEARNING WITH GPUS GEOINT 2015 Larry Brown Ph.D. June 2015 AGENDA 1 Introducing NVIDIA 2 What is Deep Learning? 3 GPUs and Deep Learning 4 cudnn and DiGiTS 5 Machine Learning & Data Analytics and

More information

arxiv:1511.02300v2 [cs.cv] 9 Mar 2016

arxiv:1511.02300v2 [cs.cv] 9 Mar 2016 Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images Shuran Song Jianxiong Xiao Princeton University http://dss.cs.princeton.edu arxiv:1511.02300v2 [cs.cv] 9 Mar 2016 Abstract We focus on

More information

An Empirical Evaluation of Current Convolutional Architectures Ability to Manage Nuisance Location and Scale Variability

An Empirical Evaluation of Current Convolutional Architectures Ability to Manage Nuisance Location and Scale Variability An Empirical Evaluation of Current Convolutional Architectures Ability to Manage Nuisance Location and Scale Variability Nikolaos Karianakis nikarianakis@ucla.edu Jingming Dong dong@cs.ucla.edu Stefano

More information

Task-driven Progressive Part Localization for Fine-grained Recognition

Task-driven Progressive Part Localization for Fine-grained Recognition Task-driven Progressive Part Localization for Fine-grained Recognition Chen Huang Zhihai He chenhuang@mail.missouri.edu University of Missouri hezhi@missouri.edu Abstract In this paper we propose a task-driven

More information

Weakly Supervised Object Boundaries Supplementary material

Weakly Supervised Object Boundaries Supplementary material Weakly Supervised Object Boundaries Supplementary material Anna Khoreva Rodrigo Benenson Mohamed Omran Matthias Hein 2 Bernt Schiele Max Planck Institute for Informatics, Saarbrücken, Germany 2 Saarland

More information

Do Deep Nets Really Need to be Deep?

Do Deep Nets Really Need to be Deep? Do Deep Nets Really Need to be Deep? Lei Jimmy Ba University of Toronto jimmy@psi.utoronto.ca Rich Caruana Microsoft Research rcaruana@microsoft.com Abstract Currently, deep neural networks are the state

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 University of Toronto kriz@cs.utoronto.ca Ilya Sutskever University of Toronto ilya@cs.utoronto.ca Geoffrey E. Hinton University

More information

Implementing Deep Neural Networks with Non Volatile Memories

Implementing Deep Neural Networks with Non Volatile Memories NeuroSTIC 2015 July 1st, 2015 Implementing Deep Neural Networks with Non Volatile Memories Olivier Bichler 1 (olivier.bichler@cea.fr) Daniele Garbin 2 Elisa Vianello 2 Luca Perniola 2 Barbara DeSalvo 2

More information

arxiv:1409.4842v1 [cs.cv] 17 Sep 2014

arxiv:1409.4842v1 [cs.cv] 17 Sep 2014 Going deeper with convolutions Christian Szegedy Wei Liu University of North Carolina, Chapel Hill Yangqing Jia arxiv:1409.4842v1 [cs.cv] 17 Sep 2014 Pierre Sermanet Scott Reed University of Michigan Vincent

More information

A Dynamic Convolutional Layer for Short Range Weather Prediction

A Dynamic Convolutional Layer for Short Range Weather Prediction A Dynamic Convolutional Layer for Short Range Weather Prediction Benjamin Klein, Lior Wolf and Yehuda Afek The Blavatnik School of Computer Science Tel Aviv University beni.klein@gmail.com, wolf@cs.tau.ac.il,

More information

Scalable Object Detection by Filter Compression with Regularized Sparse Coding

Scalable Object Detection by Filter Compression with Regularized Sparse Coding Scalable Object Detection by Filter Compression with Regularized Sparse Coding Ting-Hsuan Chao, Yen-Liang Lin, Yin-Hsi Kuo, and Winston H Hsu National Taiwan University, Taipei, Taiwan Abstract For practical

More information

arxiv:submit/1533655 [cs.cv] 13 Apr 2016

arxiv:submit/1533655 [cs.cv] 13 Apr 2016 Bags of Local Convolutional Features for Scalable Instance Search Eva Mohedano, Kevin McGuinness and Noel E. O Connor Amaia Salvador, Ferran Marqués, and Xavier Giró-i-Nieto Insight Center for Data Analytics

More information

Simple and efficient online algorithms for real world applications

Simple and efficient online algorithms for real world applications Simple and efficient online algorithms for real world applications Università degli Studi di Milano Milano, Italy Talk @ Centro de Visión por Computador Something about me PhD in Robotics at LIRA-Lab,

More information

Semantic Recognition: Object Detection and Scene Segmentation

Semantic Recognition: Object Detection and Scene Segmentation Semantic Recognition: Object Detection and Scene Segmentation Xuming He xuming.he@nicta.com.au Computer Vision Research Group NICTA Robotic Vision Summer School 2015 Acknowledgement: Slides from Fei-Fei

More information

Real-Time Grasp Detection Using Convolutional Neural Networks

Real-Time Grasp Detection Using Convolutional Neural Networks Real-Time Grasp Detection Using Convolutional Neural Networks Joseph Redmon 1, Anelia Angelova 2 Abstract We present an accurate, real-time approach to robotic grasp detection based on convolutional neural

More information

Image Captioning A survey of recent deep-learning approaches

Image Captioning A survey of recent deep-learning approaches Image Captioning A survey of recent deep-learning approaches Kiran Vodrahalli February 23, 2015 The task We want to automatically describe images with words Why? 1) It's cool 2) Useful for tech companies

More information

Going Deeper with Convolutional Neural Network for Intelligent Transportation

Going Deeper with Convolutional Neural Network for Intelligent Transportation Going Deeper with Convolutional Neural Network for Intelligent Transportation by Tairui Chen A Thesis Submitted to the Faculty of the WORCESTER POLYTECHNIC INSTITUTE In partial fulfillment of the requirements

More information

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features JT Turner 1, Kalyan Gupta 1, Brendan Morris 2, & David

More information

The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2

The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016) The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2 1 School of

More information

Large Scale Semi-supervised Object Detection using Visual and Semantic Knowledge Transfer

Large Scale Semi-supervised Object Detection using Visual and Semantic Knowledge Transfer Large Scale Semi-supervised Object Detection using Visual and Semantic Knowledge Transfer Yuxing Tang 1 Josiah Wang 2 Boyang Gao 1,3 Emmanuel Dellandréa 1 Robert Gaizauskas 2 Liming Chen 1 1 Ecole Centrale

More information