Learning Transferable Features with Deep Adaptation Networks
|
|
- Marilynn Gregory
- 5 years ago
- Views:
Transcription
1 Learning Transferable Features with Deep Adaptation Networks Mingsheng Long, Yue Cao, Jianmin Wang, Michael I. Jordan Presented by Changyou Chen October 30, Changyou Chen Learning Transferable Features with Deep Adaptation Networks
2 Outline Introduction 1 Introduction 2 Deep Adaptation Networks 3 Experiments 2 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
3 Contribution Introduction Proposes a deep architecture for transfer learning. Based on a deep convolution neural network (AlexNet [Krizhevshy et al., 2012]). It is essentially an CNN with a particular regularizer, such that the distance between the distributions generating the source domain data and target domain data is minimized. 3 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
4 Introduction Transfer learning (domain adaptation) This paper considers the unsupervised/semi-supervised domain adaptation setting. Given source domain D s = {(xi s,ys i )}n s i=1 generated from distribution p, and unlabelled target domain D t = {xj t}n t j=1 (unsupervised), or partially labelled D t = {(xi t,yt i )m t i=1,{xt j }} (semi-supervised), generated from distribution q. p and q are usually unknown. Transfer learning aims to build a classifier y = θ(x), which can minimize target risk ε t (θ) = Pr (x,y) q [θ(x) y], using source supervision: - in this paper, the classifier is built based on an CNN the AlexNet [Krizhevshy et al., 2012] 4 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
5 Introduction The AlexNet [Krizhevshy et al., 2012] 8 layers deep models, with the first five layers being CNN, the 6-7 layers fully connected layers, and the last layer a softmax layer. It got state-of-the-art classification performance on imagenet in Building block for many state-of-the-art models. 5 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
6 Introduction Multi-kernel maximum mean discrepancy (MK-MMD) MK-MMD describes distances between distributions in a reproducing kernel Hilbert space (RKHS). Let H k be an RKHS with kernel k. The mean embedding of a distribution p in H k is a unique element µ k (p) such that E x p f (x) =< f (x), µ k (p) > Hk, f H k. Given the feature map φ, MK-MMD defines the following objective as the RKHS distance between the mean embeddings of p and q: d 2 k(p,q) E p [φ(x s )] E q [φ(x t )] 2 H k (1) The kernel associated with φ is the convex combination of m PSD kernels {k u }: { } K k = m u=1 β u k u : m u=1 β u = 1,β u 0, u 6 Changyou Chen Learning Transferable Features with Deep Adaptation Networks (2)
7 Outline Deep Adaptation Networks 1 Introduction 2 Deep Adaptation Networks 3 Experiments 7 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
8 Deep Adaptation Networks Deep adaptation networks (DAN) Two parallel AlexNets with sharing: - one for the source domain, the other for the target domain - first 5 convolutional layers are shared, with the first three fixed pretrain on the source domain, last two fine-tuned in the training using the target domain data - last 3 layers are individual, feedforward nets - last layer is the softmax layer - use MK-MMD to regularize that the distributions p and q generating the data are close to each other in the RKHS 8 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
9 Deep Adaptation Networks Deep adaptation networks (DAN) Let Θ = {W l,b l } L l=1 the set of all model parameters, the objective function of DAN is: n 1 a min Θ n a J(θ(xi a ),y a 8 i ) +λ dk(d 2 l s,d l t) (3) i=1 l=6 } {{ }} {{ } CNN MK-MMD - (xi a,ya i ): labeled input data; θ(xa i ): softmax output; J: cross-entropy loss function - D l = {h l i }: l-th layer hidden representation - dk 2(Dl s,d l t) = E x s x sk(xs,x s ) + E x t x tk(xt,x t ) 2E x s x tk(xs,x t ): MK-MMD between the source and target Use an unbiased estimation of dk 2(Dl s,d l t) in SGD: dk(d 2 l s,d l t) = 2 n s /2 n s g k (z i ), (4) i=1 with z i (x s 2i 1,xs 2i,xt 2i 1,xt 2i ) and g k (z i ) k(x s 2i 1,xs 2i ) + k(xt 2i 1,xt 2i ) k(xs 2i 1,xt 2i ) k(xs 2i,xt 2i 1 ). 9 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
10 Deep Adaptation Networks Deep adaptation networks (DAN) The gradient can be calculated as: - - J(z i ) Θ l g k (z l i ) Θ l Θ l = J(z i) Θ l + λ g k(z l i ) Θ l (5) is the same as in standard CNN can also be calculated easily Learning kernel weights β: - according to [Gretton et al., 2012], this is equivalent to: min β T (Q + εi)β, (6) d T β=1,β 0 with Q a matrix constructed from g k (z i ). 10 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
11 Deep Adaptation Networks Theoretical property Theorem Let ε (θ) = Pr (x,y) [θ(x) y] be the expected risk of the source/target domain, then ε t (θ) ε s (θ) + 2d k (p,q) + C, (7) where C is a constant of the complexity of hypothesis space and the risk of an ideal hypothesis for both domains. 11 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
12 Outline Experiments 1 Introduction 2 Deep Adaptation Networks 3 Experiments 12 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
13 Datasets Experiments Office-31: - 4,652 images with 31 categories collected from: Amazon (A), Webcam (W) and DSLR (D) - evaluate transfers: A W, D W, W D, A D, D A, W A Office-10 + Caltech-10: - 10 categories shared by the Office-31 and Caltech-256 (C) datasets - evaluate transfers: A C, W C, D C, C A, C W, C D 13 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
14 Setup Experiments Compared with TCA [Pan et al., 2011], GFK [Gong et al., 2012] (shallow models), and CNN [Krizhevshy et al., 2012], LapCNN [Weston et al., 2008], DDC [Tzeng et al., 2014] (deep models). Several variants of DAN: - DAN 7 : DAN with layer 7 to impose the MK-MMD - DAN 8 : DAN with layer 8 to impose the MK-MMD - DAN SK : DAN with a single kernel MMD Using Gaussian kernels with varying bandwidth (variance). Fix convolution layers conv1 conv3 with a pretrain on the source data with the AlexNet, fine-tune conv4 conv5 and fully connected layers fc6 fc8. 14 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
15 Experiments Office-31: unsupervised 15 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
16 Experiments Office-10 + Caltech-10: unsupervised 16 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
17 Experiments Office-31: semi-supervised Deep models outperforms shallow models. Existing deep models can not deal well with the challenge of domain discrepancy. Multiple layers distribution adaptation (DAN) is better than single layer adaptation (DAN 7 or DAN 8 ), also better than single kernel variant (DAN SK ). 17 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
18 Experiments Feature embedding with t-sne 18 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
19 Experiments Thanks for your attention!!! 19 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
20 References I Experiments Gretton, A., Sriperumbudur, B., Sejdinovic, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K.: Optimal kernel choice for large-scale two-sample tests. NIPS (2012) Pan, S. J., Tsang, I. W., Kwok, J. T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks and Learning Systems (2011) Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. CVPR (2012) Krizhevshy, A., Sutskever, I., Hinton, G. E.: Imagenet classification with deep convolutional neural networks. NIPS (2012) Weston, J., Rattle, F., Collobert, R.: Deep learning via semi-supervised embedding. ICML (2008) Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: Maximising for domain invariance. Technical report, arxiv: (2014) 20 Changyou Chen Learning Transferable Features with Deep Adaptation Networks
arxiv: v1 [cs.cv] 6 Jul 2016
arxiv:607.079v [cs.cv] 6 Jul 206 Deep CORAL: Correlation Alignment for Deep Domain Adaptation Baochen Sun and Kate Saenko University of Massachusetts Lowell, Boston University Abstract. Deep neural networks
More informationarxiv: v2 [cs.lg] 17 Aug 2017
Mingsheng Long 1 Han Zhu 1 Jianmin Wang 1 Michael I. Jordan 2 arxiv:1605.06636v2 [cs.lg] 17 Aug 2017 Abstract Deep networks have been successfully applied to learn transferable features for adapting models
More informationAdapting Deep Networks Across Domains, Modalities, and Tasks Judy Hoffman!
Adapting Deep Networks Across Domains, Modalities, and Tasks Judy Hoffman! Eric Tzeng Saurabh Gupta Kate Saenko Trevor Darrell Recent Visual Recognition Progress ImageNet Performance 100 Accuracy 95 90
More informationPartial Adversarial Domain Adaptation
Partial Adversarial Domain Adaptation Zhangjie Cao, Lijia Ma, Mingsheng Long( ), and Jianmin Wang School of Software, Tsinghua University, China National Engineering Laboratory for Big Data Software Beijing
More informationUnsupervised Domain Adaptation by Domain Invariant Projection
2013 IEEE International Conference on Computer Vision Unsupervised Domain Adaptation by Domain Invariant Projection Mahsa Baktashmotlagh 1,3, Mehrtash T. Harandi 2,3, Brian C. Lovell 1, and Mathieu Salzmann
More informationProgress on Generative Adversarial Networks
Progress on Generative Adversarial Networks Wangmeng Zuo Vision Perception and Cognition Centre Harbin Institute of Technology Content Image generation: problem formulation Three issues about GAN Discriminate
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 informationarxiv: v2 [cs.cv] 28 Mar 2018
Importance Weighted Adversarial Nets for Partial Domain Adaptation Jing Zhang, Zewei Ding, Wanqing Li, Philip Ogunbona Advanced Multimedia Research Lab, University of Wollongong, Australia jz60@uowmail.edu.au,
More informationUnsupervised domain adaptation of deep object detectors
Unsupervised domain adaptation of deep object detectors Debjeet Majumdar 1 and Vinay P. Namboodiri2 Indian Institute of Technology, Kanpur - Computer Science and Engineering Kalyanpur, Kanpur, Uttar Pradesh
More informationGeodesic Flow Kernel for Unsupervised Domain Adaptation
Geodesic Flow Kernel for Unsupervised Domain Adaptation Boqing Gong University of Southern California Joint work with Yuan Shi, Fei Sha, and Kristen Grauman 1 Motivation TRAIN TEST Mismatch between different
More informationUnsupervised Domain Adaptation by Backpropagation. Chih-Hui Ho, Xingyu Gu, Yuan Qi
Unsupervised Domain Adaptation by Backpropagation Chih-Hui Ho, Xingyu Gu, Yuan Qi Problems Deep network: requires massive labeled training data. Labeled data: Available sometimes: Image recognition Speech
More informationarxiv: v2 [cs.cv] 18 Feb 2014
One-Shot Adaptation of Supervised Deep Convolutional Models arxiv:1312.6204v2 [cs.cv] 18 Feb 2014 Judy Hoffman, Eric Tzeng, Jeff Donahue UC Berkeley, EECS & ICSI {jhoffman,etzeng,jdonahue}@eecs.berkeley.edu
More informationDeep 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 informationarxiv: v2 [cs.cv] 17 Nov 2016 Abstract
Beyond Sharing Weights for Deep Domain Adaptation Artem Rozantsev Mathieu Salzmann Pascal Fua Computer Vision Laboratory, École Polytechnique Fédérale de Lausanne Lausanne, Switzerland {firstname.lastname}@epfl.ch
More informationarxiv: v1 [cs.cv] 22 Jun 2017
Deep Hashing Network for Unsupervised Domain Adaptation Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, Sethuraman Panchanathan Center for Cognitive Ubiquitous Computing, Arizona State University,
More informationOpen Set Domain Adaptation
Open Set Domain Adaptation Pau Panareda Busto 1,2 1 Airbus Group Innovations Munich, Germany pau.panareda-busto@airbus.com Juergen Gall 2 2 Computer Vision Group University of Bonn, Germany gall@iai.uni-bonn.de
More informationarxiv: v2 [cs.ro] 26 Oct 2018
Adapting control policies from simulation to reality using a pairwise loss Ulrich Viereck, Xingchao Peng, Kate Saenko, and Robert Platt arxiv:1807.10413v2 [cs.ro] 26 Oct 2018 Abstract This paper proposes
More informationRECOGNIZING HETEROGENEOUS CROSS-DOMAIN DATA VIA GENERALIZED JOINT DISTRIBUTION ADAPTATION
RECOGNIZING HETEROGENEOUS CROSS-DOMAIN DATA VIA GENERALIZED JOINT DISTRIBUTION ADAPTATION Yuan-Ting Hsieh, Shih-Yen Tao, Yao-Hung Hubert Tsai 2, Yi-Ren Yeh 3, Yu-Chiang Frank Wang 2 Department of Electrical
More informationA Novel Representation and Pipeline for Object Detection
A Novel Representation and Pipeline for Object Detection Vishakh Hegde Stanford University vishakh@stanford.edu Manik Dhar Stanford University dmanik@stanford.edu Abstract Object detection is an important
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 informationProceedings of the International MultiConference of Engineers and Computer Scientists 2018 Vol I IMECS 2018, March 14-16, 2018, Hong Kong
, March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong TABLE I CLASSIFICATION ACCURACY OF DIFFERENT PRE-TRAINED MODELS ON THE TEST DATA
More informationarxiv: v1 [cs.cv] 30 Dec 2018
DART: DOMAIN-ADVERSARIAL RESIDUAL-TRANSFER NETWORKS FOR UNSUPERVISED CROSS-DOMAIN IMAGE CLASSIFICATION A PREPRINT arxiv:1812.11478v1 [cs.cv] 30 Dec 2018 Xianghong Fang SMILE Lab Univ. of Electronic Sci
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 informationarxiv: v2 [cs.lg] 3 Nov 2018
Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation Chao Chen, Zhihong Chen, Boyuan Jiang, Xinyu Jin Institute of Information Science and Electronic Engineering
More informationarxiv: v1 [cs.cv] 19 Nov 2018
Unsupervised Domain Adaptation: An Adaptive Feature Norm Approach Ruijia Xu Guanbin Li Jihan Yang Liang Lin School of Data and Computer Science, Sun Yat-sen University, China xurj3@mail2.sysu.edu.cn, liguanbin@mail.sysu.edu.cn,
More informationGlobal Optimality in Neural Network Training
Global Optimality in Neural Network Training Benjamin D. Haeffele and René Vidal Johns Hopkins University, Center for Imaging Science. Baltimore, USA Questions in Deep Learning Architecture Design Optimization
More 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 informationTransitive Hashing Network for Heterogeneous Multimedia Retrieval
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-7) Transitive Hashing Network for Heterogeneous Multimedia Retrieval Zhangjie Cao, Mingsheng Long, Jianmin Wang, Qiang Yang
More informationDeep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization Guoliang Kang 1, Liang Zheng 1,2, Yan Yan 1, and Yi Yang 1 1 CAI, University of Technology
More informationDeep Model Adaptation using Domain Adversarial Training
Deep Model Adaptation using Domain Adversarial Training Victor Lempitsky, joint work with Yaroslav Ganin Skolkovo Institute of Science and Technology ( Skoltech ) Moscow region, Russia Deep supervised
More informationBilinear 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 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 informationEfficient 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 informationDeep Learning for Computer Vision II
IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L
More informationTransfer 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 informationDeep Asymmetric Transfer Network for Unbalanced Domain Adaptation
Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation Daixin Wang, Peng Cui, Wenwu Zhu Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and
More informationJOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS. Puyang Xu, Ruhi Sarikaya. Microsoft Corporation
JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS Puyang Xu, Ruhi Sarikaya Microsoft Corporation ABSTRACT We describe a joint model for intent detection and slot filling based
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 informationDomain Transfer SVM for Video Concept Detection
Domain Transfer SVM for Video Concept Detection Lixin Duan Ivor W. Tsang Dong Xu School of Computer Engineering Nanyang Technological University {S080003, IvorTsang, DongXu}@ntu.edu.sg Stephen J. Maybank
More informationChannel Locality Block: A Variant of Squeeze-and-Excitation
Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan
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 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 informationUnsupervised Deep Learning. James Hays slides from Carl Doersch and Richard Zhang
Unsupervised Deep Learning James Hays slides from Carl Doersch and Richard Zhang Recap from Previous Lecture We saw two strategies to get structured output while using deep learning With object detection,
More informationTransfer Feature Representation via Multiple Kernel Learning
Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence Transfer Feature Representation via Multiple Kernel Learning Wei Wang 1, Hao Wang 1,2, Chen Zhang 1, Fanjiang Xu 1 1 Science and
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 informationTransfer learning for the Probabilistic Classification Vector Machine
Proceedings of Machine Learning Research 61:1 14, 2018 Conformal and Probabilistic Prediction and Applications Transfer learning for the Probabilistic Classification Vector Machine Christoph Raab University
More informationDeep Generative Models and a Probabilistic Programming Library
Deep Generative Models and a Probabilistic Programming Library Discriminative (Deep) Learning Learn a (differentiable) function mapping from input to output x f(x; θ) y Gradient back-propagation Generative
More informationarxiv: v2 [cs.cv] 1 Aug 2016
arxiv:1607.03516v2 [cs.cv] 1 Aug 2016 Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation Muhammad Ghifary 1, W. Bastiaan Kleijn 1, Mengjie Zhang 1, David Balduzzi 1, Wen Li
More informationarxiv: v1 [cs.cv] 20 Dec 2016
End-to-End Pedestrian Collision Warning System based on a Convolutional Neural Network with Semantic Segmentation arxiv:1612.06558v1 [cs.cv] 20 Dec 2016 Heechul Jung heechul@dgist.ac.kr Min-Kook Choi mkchoi@dgist.ac.kr
More informationVisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation
VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation Xingchao Peng 1, Ben Usman 1, Neela Kaushik 1, Dequan Wang 2, Judy Hoffman 2, and Kate Saenko 1 xpeng,usmn,nkaushik,saenko@bu.edu, jhoffman,dqwang@eecs.berkeley.edu
More informationMachine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart
Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider
More informationDomain Generalization based on Transfer Component Analysis
Domain Generalization based on Transfer Component Analysis Thomas Grubinger 1, Adriana Birlutiu 1,2 Holger Schöner 1, Thomas Natschläger 1, and Tom Heskes 3 1 Data Analysis Systems, Software Competence
More informationarxiv: v1 [cs.cv] 15 Aug 2016
Transitive Hashing Network for Heterogeneous Multimedia Retrieval arxiv:608.04307v [cs.cv] 5 Aug 206 Zhangjie Cao, Mingsheng Long, and Qiang Yang School of Software, Tsinghua University, Beijing 00084,
More informationREVISITING BATCH NORMALIZATION FOR PRACTICAL DOMAIN ADAPTATION
REVISITING BATCH NORMALIZATION FOR PRACTICAL DOMAIN ADAPTATION Yanghao Li, Naiyan Wang, Jianping Shi, Jiaying Liu, Xiaodi Hou Institute of Computer Science and Technology, Peking University TuSimple SenseTime
More informationDivide and Conquer Kernel Ridge Regression
Divide and Conquer Kernel Ridge Regression Yuchen Zhang John Duchi Martin Wainwright University of California, Berkeley COLT 2013 Yuchen Zhang (UC Berkeley) Divide and Conquer KRR COLT 2013 1 / 15 Problem
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 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 informationA GENERALIZED KERNEL-BASED RANDOM K-SAMPLESETS METHOD FOR TRANSFER LEARNING * J. TAHMORESNEZHAD AND S. HASHEMI **
IJST, Transactions of Electrical Engineering, Vol. 39, No. E2, pp 193-207 Printed in The Islamic Republic of Iran, 2015 Shiraz University A GENERALIZED KERNEL-BASED RANDOM K-SAMPLESETS METHOD FOR TRANSFER
More informationUnsupervised Domain Adaptation with Regularized Domain Instance Denoising
Unsupervised Domain Adaptation with Regularized Domain Instance Denoising Gabriela Csurka, Boris Chidlowskii, Stéphane Clinchant and Sophia Michel Xerox Research Center Europe 6 chemin de Maupertuis, 38240
More informationDomain Generalization with Adversarial Feature Learning
Domain Generalization with Adversarial Feature Learning Haoliang Li 1 Sinno Jialin Pan 2 Shiqi Wang 3 Alex C. Kot 1 1 School of Electrical and Electronic Engineering, Nanyang Technological University,
More informationReal-time Object Detection CS 229 Course Project
Real-time Object Detection CS 229 Course Project Zibo Gong 1, Tianchang He 1, and Ziyi Yang 1 1 Department of Electrical Engineering, Stanford University December 17, 2016 Abstract Objection detection
More informationarxiv: v2 [cs.cv] 27 Nov 2017
Deep Supervised Discrete Hashing arxiv:1705.10999v2 [cs.cv] 27 Nov 2017 Qi Li Zhenan Sun Ran He Tieniu Tan Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition
More informationDeCAF: 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 informationIn 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 informationDeep Learning and Its Applications
Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent
More informationOverall 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 informationImproving One-Shot Learning through Fusing Side Information
Improving One-Shot Learning through Fusing Side Information Yao-Hung Hubert Tsai Ruslan Salakhutdinov Machine Learning Department, School of Computer Science, Carnegie Mellon University {yaohungt, rsalakhu}@cs.cmu.edu
More informationReal-Time Document Image Classification using Deep CNN and Extreme Learning Machines
Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki a koelsch12@cs.uni-kl.de, afzal@iupr.com, m.ebbecke@insiders-technologies.de,
More informationSupplementary 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 informationFully Convolutional Networks for Semantic Segmentation
Fully Convolutional Networks for Semantic Segmentation Jonathan Long* Evan Shelhamer* Trevor Darrell UC Berkeley Chaim Ginzburg for Deep Learning seminar 1 Semantic Segmentation Define a pixel-wise labeling
More informationFeature Selection for Transfer Learning
Feature Selection for Transfer Learning Selen Uguroglu and Jaime Carbonell Language Technologies Institute, Carnegie Mellon University {sugurogl,jgc}@cs.cmu.edu Abstract. Common assumption in most machine
More informationLandmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation
Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation Rahaf Aljundi, Re mi Emonet, Damien Muselet and Marc Sebban rahaf.aljundi@gmail.com remi.emonet, damien.muselet, marc.sebban
More informationDeep Unsupervised Convolutional Domain Adaptation
Deep Unsupervised Convolutional Domain Adaptation Junbao Zhuo 1,2, Shuhui Wang 1, Weigang Zhang 3, Qingming Huang 1,2 1 Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, 100190,
More informationDomain Separation Networks
Domain Separation Networks Konstantinos Bousmalis Google Brain Mountain View, CA konstantinos@google.com George Trigeorgis Imperial College London London, UK g.trigeorgis@imperial.ac.uk arxiv:1608.06019v1
More informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 22 March 2017 joint work with Max Welling (University of Amsterdam) BDL Workshop @ NIPS 2016
More informationPart 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 informationarxiv: v1 [cs.cv] 29 Sep 2016
arxiv:1609.09545v1 [cs.cv] 29 Sep 2016 Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge Adrian Bulat and Georgios Tzimiropoulos Computer Vision
More informationIntroduction to Deep Learning
ENEE698A : Machine Learning Seminar Introduction to Deep Learning Raviteja Vemulapalli Image credit: [LeCun 1998] Resources Unsupervised feature learning and deep learning (UFLDL) tutorial (http://ufldl.stanford.edu/wiki/index.php/ufldl_tutorial)
More informationApplication of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset
Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset Suyash Shetty Manipal Institute of Technology suyash.shashikant@learner.manipal.edu Abstract In
More informationFeature Visualization
CreativeAI: Deep Learning for Graphics Feature Visualization Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TU Munich UCL Timetable Theory and Basics State of the Art
More informationCOMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017
COMP9444 Neural Networks and Deep Learning 7. Image Processing COMP9444 17s2 Image Processing 1 Outline Image Datasets and Tasks Convolution in Detail AlexNet Weight Initialization Batch Normalization
More informationDistant Domain Transfer Learning
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) Distant Domain Transfer Learning Ben Tan, * Yu Zhang, * Sinno Jialin Pan, ** Qiang Yang * * Hong Kong University of
More informationarxiv: v1 [cs.cv] 17 Jan 2019
Deep Transfer Across Domains for Face Anti-spoofing Xiaoguang Tu 1, Hengsheng Zhang 1, Mei Xie 1, Yao Luo 1, Yuefei Zhang 2, Zheng Ma 1 1 University of Electronic Science and Technology of China, 2 Chongqing
More informationMetric Learning for Large-Scale Image Classification:
Metric Learning for Large-Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Florent Perronnin 1 work published at ECCV 2012 with: Thomas Mensink 1,2 Jakob Verbeek 2 Gabriela Csurka
More informationDeep Visual Domain Adaptation: A Survey
Manuscript accepted by Neurocomputing 2018 1 Deep Visual Domain Adaptation: A Survey Mei Wang, Weihong Deng School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,
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 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 informationLSTM: An Image Classification Model Based on Fashion-MNIST Dataset
LSTM: An Image Classification Model Based on Fashion-MNIST Dataset Kexin Zhang, Research School of Computer Science, Australian National University Kexin Zhang, U6342657@anu.edu.au Abstract. The application
More informationLayerwise Interweaving Convolutional LSTM
Layerwise Interweaving Convolutional LSTM Tiehang Duan and Sargur N. Srihari Department of Computer Science and Engineering The State University of New York at Buffalo Buffalo, NY 14260, United States
More informationEND-TO-END CHINESE TEXT RECOGNITION
END-TO-END CHINESE TEXT RECOGNITION Jie Hu 1, Tszhang Guo 1, Ji Cao 2, Changshui Zhang 1 1 Department of Automation, Tsinghua University 2 Beijing SinoVoice Technology November 15, 2017 Presentation at
More informationarxiv: v1 [cs.cv] 1 Dec 2017
Image to Image Translation for Domain Adaptation Zak Murez 1,2 Soheil Kolouri 2 David Kriegman 1 Ravi Ramamoorthi 1 Kyungnam Kim 2 1 University of California, San Diego; 2 HRL Laboratories, LLC; {zmurez,kriegman,ravir}@cs.ucsd.edu,
More informationTransfer Learning Using Rotated Image Data to Improve Deep Neural Network Performance
Transfer Learning Using Rotated Image Data to Improve Deep Neural Network Performance Telmo Amaral¹, Luís M. Silva¹², Luís A. Alexandre³, Chetak Kandaswamy¹, Joaquim Marques de Sá¹ 4, and Jorge M. Santos¹
More informationImproving the way neural networks learn Srikumar Ramalingam School of Computing University of Utah
Improving the way neural networks learn Srikumar Ramalingam School of Computing University of Utah Reference Most of the slides are taken from the third chapter of the online book by Michael Nielson: neuralnetworksanddeeplearning.com
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 Jian Sun Present by: Yixin Yang Mingdong Wang 1 Object Detection 2 1 Applications Basic
More informationPerceptron: This is convolution!
Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image
More informationarxiv: v3 [cs.lg] 1 Mar 2017
Jordan T. Ash Robert E. Schapire Barbara E. Engelhardt arxiv:6.4889v3 [cs.lg] Mar 7 Abstract Domain adaptation addresses the problem created when training data is generated by a socalled source distribution,
More informationPUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories
PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories Behnam Gholami 1, Ognjen (Oggi) Rudovic 2, Vladimir Pavlovic 1 1 Department of Computer Science, Rutgers
More informationSpatial 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 informationConstrained Convolutional Neural Networks for Weakly Supervised Segmentation. Deepak Pathak, Philipp Krähenbühl and Trevor Darrell
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation Deepak Pathak, Philipp Krähenbühl and Trevor Darrell 1 Multi-class Image Segmentation Assign a class label to each pixel in
More informationObject Detection Lecture Introduction to deep learning (CNN) Idar Dyrdal
Object Detection Lecture 10.3 - Introduction to deep learning (CNN) Idar Dyrdal Deep Learning Labels Computational models composed of multiple processing layers (non-linear transformations) Used to learn
More information