Geodesic Flow Kernel for Unsupervised Domain Adaptation
|
|
- Betty Beasley
- 5 years ago
- Views:
Transcription
1 Geodesic Flow Kernel for Unsupervised Domain Adaptation Boqing Gong University of Southern California Joint work with Yuan Shi, Fei Sha, and Kristen Grauman 1
2 Motivation TRAIN TEST Mismatch between different domains/datasets Object recognition Ex. [Torralba & Efros 11, Perronnin et al. 10] Video analysis Ex. [Duan et al. 09, 10] Pedestrian detection Ex. [Dollár et al. 09] Other vision tasks Performance degrades significantly! Images from [Saenko et al. 10]. 2
3 Unsupervised domain adaptation Source domain (labeled) D Target domain (unlabeled) Objective = {( x, y ), i = 1,2,!, N}~ P ( X, Y) S i i S D = {( x,?), i = 1,2,!, M}~ P ( X, Y) T i T The two distributions are not the same! Train classification model to work well on the target 3
4 Challenges How to optimally, w.r.t. target domain, define discriminative loss function select model, tune parameters How to solve this ill-posed problem? impose additional structure 4
5 Examples of existing approaches Correcting sample bias Ex. [Shimodaira 00, Huang et al. 06, Bickel et al. 07] Assumption: marginal distributions are the only difference. Learning transductively Ex. [Bergamo & Torresani 10, Bruzzone & Marconcini 10] Assumption: classifiers have high-confidence predictions across domains. Learning a shared representation Ex. [Daumé III 07, Pan et al. 09, Gopalan et al. 11] Assumption: a latent feature space exists in which classification hypotheses fit both domains. 5
6 Our approach: learning a shared representation Key insight: bridging the gap Fantasize infinite number of domains Integrate out analytically idiosyncrasies in domains Learn invariant features by constructing kernel Source F() t áz z, z i j Target T æf(0) ö ç ç! T = ç F() t x ç ç! ç T (1) è F ø ñ 6
7 Main idea: geodesic flow kernel F() t Source 2 Target 1 z T æf(0) ö ç ç! T = ç F() t x ç ç! ç T (1) è F ø 3 áz, z ñ i j 4 1. Model data with linear subspaces 2. Model domain shift with geodesic flow 3. Derive domain-invariant features with kernel 4. Classify target data with the new features 7
8 Modeling data with linear subspaces Assume low-dimensional structure Target Source Ex. PCA, Partial Least Squares (source only) 8
9 Characterizing domains geometrically Source subspace Target subspace Grassmann manifold G( dd, ) Collection of d-dimensional subspaces of a vector D space R ( d < D) Each point corresponds to a subspace 9
10 Modeling domain shift with geodesic flow F(0) Source F(1) F (),0 t t 1 Target Geodesic flow on the manifold starting at source & arriving at target in unit time flow parameterized with one parameter closed-form, easy to compute with SVD 10
11 Modeling domain shift with geodesic flow Subspaces: F(0) Source F(1) F (),0 t t 1 Target Domains: Source Target 11
12 Modeling domain shift with geodesic flow Subspaces: F(0) Source F(1) F (),0 t t 1 Target Domains: Along this flow, points (subspaces) represent intermediate domains. 12
13 Domain-invariant features z = [ F(0) T x,!, F( t) T x,!, F(1) T x] Source F(0) F(1) F (),0 t t 1 Target More similar to source. 13
14 Domain-invariant features z = [ F(0) T x,!, F( t) T x,!, F(1) T x] Source F(0) F(1) F (),0 t t 1 Target More similar to target. 14
15 Domain-invariant features z = [ F(0) T x,!, F( t) T x,!, F(1) T x] Source F(0) F(1) F (),0 t t 1 Target Blend the two. 15
16 Measuring feature similarities with inner products z z = T T T [ F(0) x,!, F( t) x,!, F(1) x i i i i = T T T [ F(0) x,!, F( t) x,!, F(1) x ] j j j j ] More similar to source. More similar to target. áz, z ñ: Invariant to either source or target. i j 16
17 Learning domain-invariant features with kernels We define the geodesic flow kernel (GFK): Advantages 1 T T T T i, z j ( () ) ( () ) 0 i j dt xi Gx j áz ñ = ò F t x F t x = Analytically computable Robust to variants towards either source or target Broadly applicable: can kernelize many classifiers 17
18 Contrast to discretely sampling GFK (ours) [Gopalan et al. ICCV 2011] F(0) F (),0 t t 1 F(1) áz, z ñ = ò 1 0 i j ( F() t x ) ( F ( t) x ) dt = x Gx T T T T i j i j No free parameters Dimensionality reduction GFK is conceptually cleaner and computationally more tractable. Number of subspaces, dimensionality of subspace, dimensionality after reduction 18
19 Recap of key steps 1 Source subspace 2 Target subspace ( " = )(+) - )(/) - x )(0) - 3! " ázi, z j ñ = $ % &$ ' 4 19
20 Experimental setup Four domains Features Bag-of-SURF Classifier: 1NN Average over 20 random trials Caltech-256 DSLR Amazon Webcam 20
21 Classification accuracy on target 40 No adaptation [Gopalan et al.'11] GFK (ours) Accuracy (%) W-->C W-->A C-->D C-->A A-->W A-->C D-->A SourceàTarget 21
22 Classification accuracy on target 40 No adaptation [Gopalan et al.'11] GFK (ours) Accuracy (%) W-->C W-->A C-->D C-->A A-->W A-->C D-->A SourceàTarget 22
23 Classification accuracy on target 40 No adaptation [Gopalan et al.'11] GFK (ours) Accuracy (%) W-->C W-->A C-->D C-->A A-->W A-->C D-->A SourceàTarget 23
24 Which domain should be used as the source? DSLR Caltech-256 Webcam Amazon 24
25 Automatically selecting the best We introduce the Rank of Domains measure: Intuition Geometrically, how subspaces disagree Statistically, how distributions disagree 25
26 Automatically selecting the best Possible sources Our ROD measure Caltech Amazon 0 DSLR 0.26 Webcam 0.05 Accuracy (%) No adaptation [Gopalan et al.'11] GFK (ours) W-->A C256-->A D-->A SourceàTarget Caltech-256 adapts the best to Amazon. 26
27 Semi-supervised domain adaptation Label three instances per category in the target 60 No adaptation [Gopalan et al.'11] [Saenko et al.'10] GFK (ours) Accuracy (%) W-->C W-->A C-->D C-->A A-->W A-->C D-->A SourceàTarget 27
28 Analyzing datasets in light of domain adaptation Cross-dataset generalization [Torralba & Efros 11] Accuracy (%) Self Cross (no adaptation) Cross (with adaptation) PASCAL ImageNet Caltech
29 Analyzing datasets in light of domain adaptation Cross-dataset generalization [Torralba & Efros 11] Accuracy (%) Self Cross (no adaptation) Cross (with adaptation) 70 Performance 60 drop! PASCAL ImageNet Caltech-101 Caltech-101 generalizes the worst. Performance drop of ImageNet is big. 29
30 Analyzing datasets in light of domain adaptation Cross-dataset generalization [Torralba & Efros 11] Accuracy (%) Self Cross (no adaptation) Cross (with adaptation) Performance drop becomes smaller! PASCAL ImageNet Caltech-101 Caltech-101 generalizes the worst (w/ or w/o adaptation). There is nearly no performance drop of ImageNet. 30
31 Summary Unsupervised domain adaptation Important in visual recognition Challenge: no labeled data from the target Geodesic flow kernel (GFK) Conceptually clean formulation: no free parameter Computationally tractable: closed-form solution Empirically successful: state-of-the-art results New insight on vision datasets Cross-dataset generalization with domain adaptation Leveraging existing datasets despite their idiosyncrasies 31
32 Future work Beyond subspaces Other techniques to model domain shift From GFK to statistical flow kernel Add more statistical properties to the flow Applications of GFK Ex., face recognition, video analysis 32
33 Summary Unsupervised domain adaptation Important in visual recognition Challenge: no labeled data from the target Geodesic flow kernel (GFK) Conceptually clean formulation Computationally tractable Empirically successful New insight on vision datasets Cross-dataset generalization with domain adaptation Leveraging existing datasets despite their idiosyncrasies 33
Unsupervised 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 informationarxiv: 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 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 informationFrustratingly Easy NBNN Domain Adaptation
Frustratingly Easy Domain Adaptation Tatiana Tommasi ESAT-PSI & iminds KU Leuven, Belgium ttommasi@esat.kuleuven.be Barbara Caputo University of Rome La Sapienza, Italy caputo@dis.uniroma1.it Abstract
More informationKernel Methods for Unsupervised Domain Adaptation. Boqing Gong
Kernel Methods for Unsupervised Domain Adaptation by Boqing Gong A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements
More informationLearning Transferable Features with Deep Adaptation Networks
Learning Transferable Features with Deep Adaptation Networks Mingsheng Long, Yue Cao, Jianmin Wang, Michael I. Jordan Presented by Changyou Chen October 30, 2015 1 Changyou Chen Learning Transferable Features
More informationAsymmetric and Category Invariant Feature Transformations for Domain Adaptation
Int J Comput Vis (2014) 109:28 41 DOI 10.1007/s11263-014-0719-3 Asymmetric and Category Invariant Feature Transformations for Domain Adaptation Judy Hoffman Erik Rodner Jeff Donahue Brian Kulis Kate Saenko
More informationRobust Visual Knowledge Transfer via Extreme Learning Machine Based Domain Adaptation
Robust Visual Knowledge Transfer via Extreme Learning Machine Based Domain Adaptation Lei Zhang, Member, IEEE and David Zhang, Fellow, IEEE Abstract We address the problem of visual knowledge adaptation
More informationLearning Partially Shared Dictionaries for Domain Adaptation
Learning Partially Shared Dictionaries for Domain Adaptation Viresh Ranjan 1 Gaurav Harit 2 C. V. Jawahar 1 1 CVIT, IIIT Hyderabad, India 2 IIT Jodhpur, India Abstract. Real world applicability of many
More informationDictionaries, Manifolds and Domain Adaptation for Image and Videobased. Rama Chellappa University of Maryland
Dictionaries, Manifolds and Domain Adaptation for Image and Videobased Recognition Rama Chellappa University of Maryland Student and the teachers Major points Training and testing data come from 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 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 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 informationMind the Gap: Subspace based Hierarchical Domain Adaptation
Mind the Gap: Subspace based Hierarchical Domain Adaptation Anant Raj IIT Kanpur Kanpur, India 208016 anantraj@iitk.ac.in Vinay P. Namboodiri IIT Kanpur Kanpur, India 208016 vinaypn@iitk.ac.in Tinne Tuytelaars
More informationBeyond bags of features: Adding spatial information. Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba Adding spatial information Forming vocabularies from pairs of nearby features doublets
More informationSemi-Supervised Domain Adaptation with Instance Constraints
Semi-Supervised Domain Adaptation with Instance Constraints Jeff Donahue 1,2, Judy Hoffman 1,2, Erik Rodner 2,3, Kate Saenko 4, Trevor Darrell 1,2 1 UC Berkeley EECS, 2 UC Berkeley ICSI, 3 University of
More informationLatent Domains Modeling for Visual Domain Adaptation
Latent Domains Modeling for Visual Domain Adaptation Caiming Xiong SUNY at Buffalo cxiong@buffalo.edu Scott McCloskey Honeywell ACS Scott.McCloskey@honeywell.com Shao-Hang Hsieh SUNY at Buffalo shaohang@buffalo.edu
More informationUndoing the Damage of Dataset Bias
Undoing the Damage of Dataset Bias Aditya Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei A. Efros, and Antonio Torralba Massachusetts Institute of Technology Carnegie Mellon University {khosla,tomasz,torralba}@csail.mit.edu,
More informationGeneralized Domain-Adaptive Dictionaries
2013 IEEE Conference on Computer Vision and Pattern Recognition Generalized Domain-Adaptive Dictionaries Sumit Shekhar Vishal M. Patel Hien V. Nguyen Rama Chellappa University of Maryland, College Park,
More informationCS 229 Midterm Review
CS 229 Midterm Review Course Staff Fall 2018 11/2/2018 Outline Today: SVMs Kernels Tree Ensembles EM Algorithm / Mixture Models [ Focus on building intuition, less so on solving specific problems. Ask
More informationA Taxonomy of Semi-Supervised Learning Algorithms
A Taxonomy of Semi-Supervised Learning Algorithms Olivier Chapelle Max Planck Institute for Biological Cybernetics December 2005 Outline 1 Introduction 2 Generative models 3 Low density separation 4 Graph
More informationDomain Adaptive Object Detection
Domain Adaptive Object Detection Fatemeh Mirrashed, Vlad I. Morariu, Behjat Siddiquie2, Rogerio S. Feris3, Larry S. Davis 2 3 University of Maryland, College Park SRI International IBM Research {fatemeh,morariu,lsd}@umiacs.umd.edu
More informationVisual Domain Adaptation: An Overview of. Recent Advances
Visual Domain Adaptation: An Overview of 1 Recent Advances Vishal M. Patel, Member, IEEE, Raghuraman Gopalan, Member, IEEE, Ruonan Li, and Rama Chellappa, Fellow, IEEE Abstract In pattern recognition and
More informationSubspace Alignment Based Domain Adaptation for RCNN Detector
RAJ, NAMBOODIRI, TUYTELAARS: ADAPTING RCNN DETECTOR 1 Subspace Alignment Based Domain Adaptation for RCNN Detector Anant Raj anantraj@iitk.ac.in Vinay P. Namboodiri vinaypn@iitk.ac.in Tinne Tuytelaars
More informationDimension Reduction CS534
Dimension Reduction CS534 Why dimension reduction? High dimensionality large number of features E.g., documents represented by thousands of words, millions of bigrams Images represented by thousands of
More informationA (somewhat) Unified Approach to Semisupervised and Unsupervised Learning
A (somewhat) Unified Approach to Semisupervised and Unsupervised Learning Ben Recht Center for the Mathematics of Information Caltech April 11, 2007 Joint work with Ali Rahimi (Intel Research) Overview
More informationObject and Action Detection from a Single Example
Object and Action Detection from a Single Example Peyman Milanfar* EE Department University of California, Santa Cruz *Joint work with Hae Jong Seo AFOSR Program Review, June 4-5, 29 Take a look at this:
More informationImproving Recognition through Object Sub-categorization
Improving Recognition through Object Sub-categorization Al Mansur and Yoshinori Kuno Graduate School of Science and Engineering, Saitama University, 255 Shimo-Okubo, Sakura-ku, Saitama-shi, Saitama 338-8570,
More informationAggregating Descriptors with Local Gaussian Metrics
Aggregating Descriptors with Local Gaussian Metrics Hideki Nakayama Grad. School of Information Science and Technology The University of Tokyo Tokyo, JAPAN nakayama@ci.i.u-tokyo.ac.jp Abstract Recently,
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
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 informationCS6375: Machine Learning Gautam Kunapuli. Mid-Term Review
Gautam Kunapuli Machine Learning Data is identically and independently distributed Goal is to learn a function that maps to Data is generated using an unknown function Learn a hypothesis that minimizes
More informationCS4495/6495 Introduction to Computer Vision. 8C-L1 Classification: Discriminative models
CS4495/6495 Introduction to Computer Vision 8C-L1 Classification: Discriminative models Remember: Supervised classification Given a collection of labeled examples, come up with a function that will predict
More informationSlides for Data Mining by I. H. Witten and E. Frank
Slides for Data Mining by I. H. Witten and E. Frank 7 Engineering the input and output Attribute selection Scheme-independent, scheme-specific Attribute discretization Unsupervised, supervised, error-
More informationAdaptive Transductive Transfer Machines
FARAJIDAVAR ET AL.: ADAPTIVE TRANSDUCTIVE TRANSFER MACHINES 1 Adaptive Transductive Transfer Machines Nazli Farajidavar http://personal.ee.surrey.ac.uk/personal/n.farajidavar Teofilo decampos http://personal.ee.surrey.ac.uk/personal/t.decampos
More informationTransductive Transfer Machine
Transductive Transfer Machine Nazli Farajidavar, Teofilo decampos, Josef Kittler CVSSP, Univeristy of Surrey, Guildford, Surrey, UK GU2 7XH Abstract. We propose a pipeline for transductive transfer learning
More informationDay 3 Lecture 1. Unsupervised Learning
Day 3 Lecture 1 Unsupervised Learning Semi-supervised and transfer learning Myth: you can t do deep learning unless you have a million labelled examples for your problem. Reality You can learn useful representations
More informationClass 5: Attributes and Semantic Features
Class 5: Attributes and Semantic Features Rogerio Feris, Feb 21, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Project
More informationMachine Learning Techniques for Data Mining
Machine Learning Techniques for Data Mining Eibe Frank University of Waikato New Zealand 10/25/2000 1 PART VII Moving on: Engineering the input and output 10/25/2000 2 Applying a learner is not all Already
More informationKernelized Bayesian Transfer Learning
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence Kernelized Bayesian Transfer Learning Mehmet Gönen mehmetgonen@sagebaseorg Sage Bionetworks Seattle, WA 9809, USA Adam A Margolin
More informationFast Indexing and Search. Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation
Fast Indexing and Search Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation Motivation Object categorization? http://www.cs.utexas.edu/~grauman/slides/jain_et_al_cvpr2008.ppt Motivation
More informationGraph and Subspace Learning for Domain Adaptation
Graph and Subspace Learning for Domain Adaptation A Dissertation Submitted to the Temple University Graduate Board in Partial Fulfillment of the Requirements for the Degree of DOCTOR OF PHILOSOPHY by Le
More informationUnified Deep Supervised Domain Adaptation and Generalization
Unified Deep Supervised Domain Adaptation and Generalization Saeid Motiian Marco Piccirilli Donald A. Adjeroh Gianfranco Doretto West Virginia University Morgantown, WV 26508 {samotiian, mpiccir1, daadjeroh,
More informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 5th, 2016 Today Administrivia LSTM Attribute in computer vision, by Abdullah and Samer Project II posted, due
More informationSketchable Histograms of Oriented Gradients for Object Detection
Sketchable Histograms of Oriented Gradients for Object Detection No Author Given No Institute Given Abstract. In this paper we investigate a new representation approach for visual object recognition. The
More informationUnsupervised learning in Vision
Chapter 7 Unsupervised learning in Vision The fields of Computer Vision and Machine Learning complement each other in a very natural way: the aim of the former is to extract useful information from visual
More informationBig Data Methods. Chapter 5: Machine learning. Big Data Methods, Chapter 5, Slide 1
Big Data Methods Chapter 5: Machine learning Big Data Methods, Chapter 5, Slide 1 5.1 Introduction to machine learning What is machine learning? Concerned with the study and development of algorithms that
More informationUlas Bagci
CAP5415-Computer Vision Lecture 14-Decision Forests for Computer Vision Ulas Bagci bagci@ucf.edu 1 Readings Slide Credits: Criminisi and Shotton Z. Tu R.Cipolla 2 Common Terminologies Randomized Decision
More informationImage Analogies for Visual Domain Adaptation
Image Analogies for Visual Domain Adaptation Jeff Donahue UC Berkeley EECS jdonahue@eecs.berkeley.edu Abstract In usual approaches to visual domain adaptation, algorithms are used to infer a common domain
More informationPouya Kousha Fall 2018 CSE 5194 Prof. DK Panda
Pouya Kousha Fall 2018 CSE 5194 Prof. DK Panda 1 Observe novel applicability of DL techniques in Big Data Analytics. Applications of DL techniques for common Big Data Analytics problems. Semantic indexing
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 informationDiscriminative classifiers for image recognition
Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study
More informationon learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015
on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 Vector visual representation Fixed-size image representation High-dim (100 100,000) Generic, unsupervised: BoW,
More informationDistances and Kernels. Motivation
Distances and Kernels Amirshahed Mehrtash Motivation How similar? 1 Problem Definition Designing a fast system to measure the similarity il it of two images. Used to categorize images based on appearance.
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 informationSubject. Dataset. Copy paste feature of the diagram. Importing the dataset. Copy paste feature into the diagram.
Subject Copy paste feature into the diagram. When we define the data analysis process into Tanagra, it is possible to copy components (or entire branches of components) towards another location into the
More informationPart based models for recognition. Kristen Grauman
Part based models for recognition Kristen Grauman UT Austin Limitations of window-based models Not all objects are box-shaped Assuming specific 2d view of object Local components themselves do not necessarily
More informationAnnouncements. Recognition I. Gradient Space (p,q) What is the reflectance map?
Announcements I HW 3 due 12 noon, tomorrow. HW 4 to be posted soon recognition Lecture plan recognition for next two lectures, then video and motion. Introduction to Computer Vision CSE 152 Lecture 17
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 informationStatic Gesture Recognition with Restricted Boltzmann Machines
Static Gesture Recognition with Restricted Boltzmann Machines Peter O Donovan Department of Computer Science, University of Toronto 6 Kings College Rd, M5S 3G4, Canada odonovan@dgp.toronto.edu Abstract
More informationMixtures 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 informationSVM-KNN : Discriminative Nearest Neighbor Classification for Visual Category Recognition
SVM-KNN : Discriminative Nearest Neighbor Classification for Visual Category Recognition Hao Zhang, Alexander Berg, Michael Maire Jitendra Malik EECS, UC Berkeley Presented by Adam Bickett Objective Visual
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 informationAction recognition in videos
Action recognition in videos Cordelia Schmid INRIA Grenoble Joint work with V. Ferrari, A. Gaidon, Z. Harchaoui, A. Klaeser, A. Prest, H. Wang Action recognition - goal Short actions, i.e. drinking, sit
More informationOverview Citation. ML Introduction. Overview Schedule. ML Intro Dataset. Introduction to Semi-Supervised Learning Review 10/4/2010
INFORMATICS SEMINAR SEPT. 27 & OCT. 4, 2010 Introduction to Semi-Supervised Learning Review 2 Overview Citation X. Zhu and A.B. Goldberg, Introduction to Semi- Supervised Learning, Morgan & Claypool Publishers,
More informationLearning Discrete Representations via Information Maximizing Self-Augmented Training
A. Relation to Denoising and Contractive Auto-encoders Our method is related to denoising auto-encoders (Vincent et al., 2008). Auto-encoders maximize a lower bound of mutual information (Cover & Thomas,
More informationScene Segmentation in Adverse Vision Conditions
Scene Segmentation in Adverse Vision Conditions Evgeny Levinkov Max Planck Institute for Informatics, Saarbrücken, Germany levinkov@mpi-inf.mpg.de Abstract. Semantic road labeling is a key component of
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 informationRandom projection for non-gaussian mixture models
Random projection for non-gaussian mixture models Győző Gidófalvi Department of Computer Science and Engineering University of California, San Diego La Jolla, CA 92037 gyozo@cs.ucsd.edu Abstract Recently,
More informationK Nearest Neighbor Wrap Up K- Means Clustering. Slides adapted from Prof. Carpuat
K Nearest Neighbor Wrap Up K- Means Clustering Slides adapted from Prof. Carpuat K Nearest Neighbor classification Classification is based on Test instance with Training Data K: number of neighbors that
More informationMachine Learning / Jan 27, 2010
Revisiting Logistic Regression & Naïve Bayes Aarti Singh Machine Learning 10-701/15-781 Jan 27, 2010 Generative and Discriminative Classifiers Training classifiers involves learning a mapping f: X -> Y,
More informationConvolutional-Recursive Deep Learning for 3D Object Classification
Convolutional-Recursive Deep Learning for 3D Object Classification Richard Socher, Brody Huval, Bharath Bhat, Christopher D. Manning, Andrew Y. Ng NIPS 2012 Iro Armeni, Manik Dhar Motivation Hand-designed
More 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 informationTopic 4: Support Vector Machines
CS 4850/6850: Introduction to achine Learning Fall 2018 Topic 4: Support Vector achines Instructor: Daniel L Pimentel-Alarcón c Copyright 2018 41 Introduction Support vector machines (SVs) are considered
More informationChapter 7. Conclusions and Future Work
Chapter 7 Conclusions and Future Work In this dissertation, we have presented a new way of analyzing a basic building block in computer graphics rendering algorithms the computational interaction between
More informationLarge scale object/scene recognition
Large scale object/scene recognition Image dataset: > 1 million images query Image search system ranked image list Each image described by approximately 2000 descriptors 2 10 9 descriptors to index! Database
More informationInterpretable Domain Adaptation via Optimization over the Stiefel Manifold
Noname manuscript No. (will be inserted by the editor) Interpretable Domain Adaptation via Optimization over the Stiefel Manifold Christian Pölitz 1 Wouter Duivesteijn 2 Katharina Morik 1 Abstract In domain
More informationLearning Compact Visual Attributes for Large-scale Image Classification
Learning Compact Visual Attributes for Large-scale Image Classification Yu Su and Frédéric Jurie GREYC CNRS UMR 6072, University of Caen Basse-Normandie, Caen, France {yu.su,frederic.jurie}@unicaen.fr
More informationLocality Preserving Projections (LPP) Abstract
Locality Preserving Projections (LPP) Xiaofei He Partha Niyogi Computer Science Department Computer Science Department The University of Chicago The University of Chicago Chicago, IL 60615 Chicago, IL
More informationBeyond Bags of Features
: for Recognizing Natural Scene Categories Matching and Modeling Seminar Instructed by Prof. Haim J. Wolfson School of Computer Science Tel Aviv University December 9 th, 2015
More informationMulti-Level Active Prediction of Useful Image Annotations
Multi-Level Active Prediction of Useful Image Annotations Sudheendra Vijayanarasimhan and Kristen Grauman Department of Computer Sciences University of Texas at Austin Austin, Texas 78712 (svnaras,grauman)@cs.utexas.edu
More informationSubspace Clustering. Weiwei Feng. December 11, 2015
Subspace Clustering Weiwei Feng December 11, 2015 Abstract Data structure analysis is an important basis of machine learning and data science, which is now widely used in computational visualization problems,
More informationAn Adaptive Framework for Multistream Classification
An Adaptive Framework for Multistream Classification Swarup Chandra, Ahsanul Haque, Latifur Khan and Charu Aggarwal* University of Texas at Dallas *IBM Research This material is based upon work supported
More informationSemi-Supervised Hierarchical Models for 3D Human Pose Reconstruction
Semi-Supervised Hierarchical Models for 3D Human Pose Reconstruction Atul Kanaujia, CBIM, Rutgers Cristian Sminchisescu, TTI-C Dimitris Metaxas,CBIM, Rutgers 3D Human Pose Inference Difficulties Towards
More informationCSE 573: Artificial Intelligence Autumn 2010
CSE 573: Artificial Intelligence Autumn 2010 Lecture 16: Machine Learning Topics 12/7/2010 Luke Zettlemoyer Most slides over the course adapted from Dan Klein. 1 Announcements Syllabus revised Machine
More informationMultiple-Choice Questionnaire Group C
Family name: Vision and Machine-Learning Given name: 1/28/2011 Multiple-Choice naire Group C No documents authorized. There can be several right answers to a question. Marking-scheme: 2 points if all right
More informationDomain Adaptation for Structured Regression
Domain Adaptation for Structured Regression Makoto Yamada, Yi Chang, Leonid Sigal 2 Yahoo Labs, 7 st Ave., Sunnyvale, 9489, USA 2 Disney Research, 472 Forbes Ave., Pittsburgh, PA 523, USA makotoy@yahoo-inc.com,
More informationCSE 6242 A / CS 4803 DVA. Feb 12, Dimension Reduction. Guest Lecturer: Jaegul Choo
CSE 6242 A / CS 4803 DVA Feb 12, 2013 Dimension Reduction Guest Lecturer: Jaegul Choo CSE 6242 A / CS 4803 DVA Feb 12, 2013 Dimension Reduction Guest Lecturer: Jaegul Choo Data is Too Big To Do Something..
More informationData Mining: Concepts and Techniques. Chapter 9 Classification: Support Vector Machines. Support Vector Machines (SVMs)
Data Mining: Concepts and Techniques Chapter 9 Classification: Support Vector Machines 1 Support Vector Machines (SVMs) SVMs are a set of related supervised learning methods used for classification Based
More informationPreparation Meeting. Recent Advances in the Analysis of 3D Shapes. Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers
Preparation Meeting Recent Advances in the Analysis of 3D Shapes Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers What You Will Learn in the Seminar Get an overview on state of the art
More informationLearning Better Data Representation using Inference-Driven Metric Learning
Learning Better Data Representation using Inference-Driven Metric Learning Paramveer S. Dhillon CIS Deptt., Univ. of Penn. Philadelphia, PA, U.S.A dhillon@cis.upenn.edu Partha Pratim Talukdar Search Labs,
More informationSemi-supervised Learning
Semi-supervised Learning Piyush Rai CS5350/6350: Machine Learning November 8, 2011 Semi-supervised Learning Supervised Learning models require labeled data Learning a reliable model usually requires plenty
More informationLinear Discriminant Analysis for 3D Face Recognition System
Linear Discriminant Analysis for 3D Face Recognition System 3.1 Introduction Face recognition and verification have been at the top of the research agenda of the computer vision community in recent times.
More informationBi-shifting Auto-Encoder for Unsupervised Domain Adaptation
Bi-shifting Auto-Encoder for Unsupervised Domain Adaptation Meina Kan 1, Shiguang Shan 1,2, Xilin Chen 1 1 Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute
More informationObject Recognition. Lecture 11, April 21 st, Lexing Xie. EE4830 Digital Image Processing
Object Recognition Lecture 11, April 21 st, 2008 Lexing Xie EE4830 Digital Image Processing http://www.ee.columbia.edu/~xlx/ee4830/ 1 Announcements 2 HW#5 due today HW#6 last HW of the semester Due May
More informationEfficient Kernels for Identifying Unbounded-Order Spatial Features
Efficient Kernels for Identifying Unbounded-Order Spatial Features Yimeng Zhang Carnegie Mellon University yimengz@andrew.cmu.edu Tsuhan Chen Cornell University tsuhan@ece.cornell.edu Abstract Higher order
More informationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun Presented by Tushar Bansal Objective 1. Get bounding box for all objects
More informationDescribable Visual Attributes for Face Verification and Image Search
Advanced Topics in Multimedia Analysis and Indexing, Spring 2011, NTU. 1 Describable Visual Attributes for Face Verification and Image Search Kumar, Berg, Belhumeur, Nayar. PAMI, 2011. Ryan Lei 2011/05/05
More informationLocal Features based Object Categories and Object Instances Recognition
Local Features based Object Categories and Object Instances Recognition Eric Nowak Ph.D. thesis defense 17th of March, 2008 1 Thesis in Computer Vision Computer vision is the science and technology of
More information