Generalized Zero-Shot Learning with Deep Calibration Network
|
|
- Claude Golden
- 5 years ago
- Views:
Transcription
1 Generalized Zero-Shot Learning with Deep Calibration Network Shichen Liu, Mingsheng Long, Jianmin Wang, and Michael I.Jordan School of Software, Tsinghua University, China KLiss, MOE; BNRist; Research Center for Big Data, Tsinghua University, China University of California, Berkeley, Berkeley, USA Youngnam Kim Machine Learning Group Department of Computer Science and Engineering Pohang University of Science and Technology
2 Preliminary Class semantic representation Class semantic representation have information on the class such as hand-labeled attribute vectors or text descriptions. Figure: Attribute vectors on AWA dataset (Xian et al., 2017)
3 Preliminary Class semantic representation Class semantic representation have information on the class such as hand-labeled attribute vectors or text descriptions. Figure: Text description on CUP dataset (Annonymous, 2018)
4 Preliminary Zero-shot learning Seen class dataset D s = {(x (s) i i-th example s label y (s) i, y (s) i )} Ns i=1, {1,..., C s } and semantic representations S s = {s (s) i Unseen class dataset D u = {x (u) i } Nu semantic representations S u = {s (u) i } Cs i=1 i=1 and } Cu i=1 where N s is the number of seen class examples, C s is the number of seen classes, N u is the number of unseen class examples and C u is the number of unseen classes. S s and S u are disjoint
5 Preliminary Zero-shot learning Train a model (φ, ψ) using seen class dataset D s and semantic representations S s Define f c (x) = sim(φ(x), ψ(s (u) c )) Prediction: y (u) i = argmax c f c (x (u) i ) Sometimes people use unseen class semantic representations S u (Liu et al., 2018) or even unseen class examples D u (Zhao et al., 2018)
6 Preliminary Generalized zero-shot learning Standard zero-shot learning: Predict sample s label over only unseen classes. Generalized zero-shot learning: Predict sample s label over both seen and unseen classes. For all semantic representations S = {s i } Cs+Cu i=1 Define f c (x) = sim(φ(x), ψ(s c )) Predict y i = argmax c f c (x i )
7 Motivation Deep learning models are likely to overfit to seen classes examples and have overconfidence to seen classes examples (almost close to 1) Model s prediction becomes uncertain when unseen classes are introduced at test time. Over-confidence on seen class samples and uncertainty on unseen class samples hurt zero-shot learning accuracy
8 Motivation
9 Prediction function Embedding of a sample x i ; φ(x i ) R k Embedding of a semantic representation s c ; ψ(s c ) R k Define f c (x i ) = sim(φ(x i ), ψ(s c )); similarity measure like inner product and cosine similarity Prediction; y i = argmax c f c (x i ) φ is a CNN (e.g. GoogLeNet-v2, ResNet-101) and ψ is a MLP
10 Loss function Sample x s class probability q over seen classes, τ is temperature exp (f c (x)/τ) q(y = c x) = Cs c =1 exp (f c (x)/τ) (1) Let ground truth class probability p(y = c x) Cross entropy loss L L = E x [ Ey x p [ log q(y x) ]] (2) Using τ < 1 to mitigate overconfidence problem over seen classes samples
11 Multi class hinge loss Most zero-shot learning methods used multi-class hinge loss; (y i, c) is 0 when y i equals to c and 1 otherwise. N s C s max(0, (y i, c) + f c (x i ) f yi (x i )) (3) i=1 c=1 If f yi (x i ) f c (x i ) < (y i, c), than [ min fc (x i ) f yi (x i ) ] (4) φ,ψ This paper shows that cross entropy loss has an advantage on zero-shot classification accuracy, compared to multi-class hinge loss.
12 Uncertainty calibration Samples x s class probability q c (u) over unseen classes S u ; f c (u) (x) is simmilarity between embedding of unseen class c and embedding of sample x Entropy loss H q (u) c (y = c x) = exp(f c (u) (x)/τ) (u) exp(f c (x)/τ) Cu c =1 (5) Total loss function of DCN [ [ (u) H = E x Ey x q (u) log q c (y x) ]] (6) c min L + λh + γω(φ, ψ) (7) φ,ψ
13 Experiments Datasets Animals with Attributes (AwA); coarse-grained and medium-scale. Caltech-UCSD-Birds (CUB); fine-grained and medium-scale. SUN Attribute (SUN); fine-graiend and medium-scale. Attribute Pascal and Yahoo (apy) coarse-grained and small-scale
14 Experiments
15 Evaluation protocol Per-class classification accuracy ACC C = 1 #correctly predicted samples in class c C #samples in class c c C (8) Generalized zero-shot learning ACC H = 2ACC unseen ACC seen ACC unseen + ACC unseen (9)
16 Experimental results DCN w/o ET; DCN without entropy loss and temperature calibration DCN w E; DCN without entropy loss
17 Experimental results
18 Experimental results
19 Analysis Temperature calibration mitigates overconfidence problem
20 Other zero-shot learning papers Stacked semantic-guided attention model for fine-grained zero-shot learning (Yu et al., 2018) Domain-invariant projection learning for zero-shot recognition (Zhao et al., 2018) Feature generating networks for zero-shot learning (Xian et al., 2018) Corelation network: meta learning for zero-shot learning (Annonymous, 2018)
21 References Annonymous. Correction networks: Meta-learning for zero-shot learning S. Liu, M. Long, J. Wang, and M. Jordan. Generalized zero-shot learning with deep calibration network. NIPS, Y. Xian, B. Schiele, and Z. Akata. Zero-shot learning-the good, the bad and the ugly. arxiv preprint arxiv: , Y. Xian, T. Lorenz, B. Schiele, and Z. Akata. Feature generating networks for zero-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, Y. Yu, Z. Ji, Y. Fu, J. Guo, Y. Pang, and Z. Zhang. Stacked semantic-guided attention model for fine-grained zero-shot learning. arxiv preprint arxiv: , A. Zhao, M. Ding, J. Guan, Z. Lu, T. Xiang, and J.-R. Wen. Domain-invariant projection learning for zero-shot recognition. arxiv preprint arxiv: , 2018.
Memory-Augmented Attention Model for Scene Text Recognition
Memory-Augmented Attention Model for Scene Text Recognition Cong Wang 1,2, Fei Yin 1,2, Cheng-Lin Liu 1,2,3 1 National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences
More informationDIVERSITY REGULARIZATION IN DEEP ENSEMBLES
Workshop track - ICLR 8 DIVERSITY REGULARIZATION IN DEEP ENSEMBLES Changjian Shui, Azadeh Sadat Mozafari, Jonathan Marek, Ihsen Hedhli, Christian Gagné Computer Vision and Systems Laboratory / REPARTI
More informationTwo at Once: Enhancing Learning and Generalization Capacities via IBN-Net
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net Supplementary Material Xingang Pan 1, Ping Luo 1, Jianping Shi 2, and Xiaoou Tang 1 1 CUHK-SenseTime Joint Lab, The Chinese University
More informationA Simple Exponential Family Framework for Zero-Shot Learning
A Simple Exponential Family Framework for Zero-Shot Learning Vinay Kumar Verma and Piyush Rai Dept. of Computer Science & Engineering, IIT Kanpur, India {vkverma,piyush}@cse.iitk.ac.in Abstract. We present
More informationVisual meta-learning for planning and control
Visual meta-learning for planning and control Seminar on Current Works in Computer Vision @ Chair of Pattern Recognition and Image Processing. Samuel Roth Winter Semester 2018/19 Albert-Ludwigs-Universität
More informationDifferentiable Fine-grained Quantization for Deep Neural Network Compression
Differentiable Fine-grained Quantization for Deep Neural Network Compression Hsin-Pai Cheng hc218@duke.edu Yuanjun Huang University of Science and Technology of China Anhui, China yjhuang@mail.ustc.edu.cn
More informationToward Correlating and Solving Abstract Tasks Using Convolutional Neural Networks Supplementary Material
Toward Correlating and Solving Abstract Tasks Using Convolutional Neural Networks Supplementary Material Kuan-Chuan Peng Cornell University kp388@cornell.edu Tsuhan Chen Cornell University tsuhan@cornell.edu
More informationDomain adaptation for deep learning
What you saw is not what you get Domain adaptation for deep learning Kate Saenko Successes of Deep Learning in AI A Learning Advance in Artificial Intelligence Rivals Human Abilities Deep Learning for
More informationTensor network vs Machine learning. Song Cheng ( 程嵩 ) IOP, CAS
Tensor network vs Machine learning Song Cheng ( 程嵩 ) IOP, CAS physichengsong@iphy.ac.cn Outline Tensor network in a nutshell TN concepts in machine learning TN methods in machine learning Outline Tensor
More informationActive Learning with Cross-class Similarity Transfer
Active Learning with Cross-class Similarity Transfer Yuchen Guo, Guiguang Ding, Yue Gao, Jungong Han Tsinghua National Laboratory for Information Science and Technology (TNList School of Software, Tsinghua
More informationBayesian Deep Learning
Bayesian Deep Learning Mohammad Emtiyaz Khan AIP (RIKEN), Tokyo http://emtiyaz.github.io emtiyaz.khan@riken.jp June 06, 2018 Mohammad Emtiyaz Khan 2018 1 What will you learn? Why is Bayesian inference
More informationCorrelation Autoencoder Hashing for Supervised Cross-Modal Search
Correlation Autoencoder Hashing for Supervised Cross-Modal Search Yue Cao, Mingsheng Long, Jianmin Wang, and Han Zhu School of Software Tsinghua University The Annual ACM International Conference on Multimedia
More informationIntroduction to Convolutional Neural Networks 2018 / 02 / 23
Introduction to Convolutional Neural Networks 2018 / 02 / 23 Buzzword: CNN Convolutional neural networks (CNN, ConvNet) is a class of deep, feed-forward (not recurrent) artificial neural networks that
More informationFace Recognition Using Global Gabor Filter in Small Sample Case *
ISSN 1673-9418 CODEN JKYTA8 E-mail: fcst@public2.bta.net.cn Journal of Frontiers of Computer Science and Technology http://www.ceaj.org 1673-9418/2010/04(05)-0420-06 Tel: +86-10-51616056 DOI: 10.3778/j.issn.1673-9418.2010.05.004
More informationAsaf Bar Zvi Adi Hayat. Semantic Segmentation
Asaf Bar Zvi Adi Hayat Semantic Segmentation Today s Topics Fully Convolutional Networks (FCN) (CVPR 2015) Conditional Random Fields as Recurrent Neural Networks (ICCV 2015) Gaussian Conditional random
More informationBeyond finite layer neural network
Beyond finite layer neural network Bridging Numerical Dynamic System And Deep Neural Networks arxiv:1710.10121 Joint work with Bin Dong, Quanzheng Li, Aoxiao Zhong Yiping Lu Peiking University School Of
More informationFine-grained Classification
Fine-grained Classification Marcel Simon Department of Mathematics and Computer Science, Germany marcel.simon@uni-jena.de http://www.inf-cv.uni-jena.de/ Seminar Talk 23.06.2015 Outline 1 Motivation 2 3
More informationFew-shot learning with KRR
Few-shot learning with KRR Prudencio Tossou Groupe de Recherche en Apprentissage Automatique Départment d informatique et de génie logiciel Université Laval April 6, 2018 Prudencio Tossou (UL) Few-shot
More informationarxiv: v1 [cs.cv] 11 May 2015 Abstract
Training Deeper Convolutional Networks with Deep Supervision Liwei Wang Computer Science Dept UIUC lwang97@illinois.edu Chen-Yu Lee ECE Dept UCSD chl260@ucsd.edu Zhuowen Tu CogSci Dept UCSD ztu0@ucsd.edu
More informationPrediction of Citations for Academic Papers
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
More informationRAGAV VENKATESAN VIJETHA GATUPALLI BAOXIN LI NEURAL DATASET GENERALITY
RAGAV VENKATESAN VIJETHA GATUPALLI BAOXIN LI NEURAL DATASET GENERALITY SIFT HOG ALL ABOUT THE FEATURES DAISY GABOR AlexNet GoogleNet CONVOLUTIONAL NEURAL NETWORKS VGG-19 ResNet FEATURES COMES FROM DATA
More informationStochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization Shai Shalev-Shwartz and Tong Zhang School of CS and Engineering, The Hebrew University of Jerusalem Optimization for Machine
More information2017 Fall ECE 692/599: Binary Representation Learning for Large Scale Visual Data
2017 Fall ECE 692/599: Binary Representation Learning for Large Scale Visual Data Liu Liu Instructor: Dr. Hairong Qi University of Tennessee, Knoxville lliu25@vols.utk.edu September 21, 2017 Liu Liu (UTK)
More informationFinite-time hybrid synchronization of time-delay hyperchaotic Lorenz system
ISSN 1746-7659 England UK Journal of Information and Computing Science Vol. 10 No. 4 2015 pp. 265-270 Finite-time hybrid synchronization of time-delay hyperchaotic Lorenz system Haijuan Chen 1 * Rui Chen
More informationCS4495/6495 Introduction to Computer Vision. 8C-L3 Support Vector Machines
CS4495/6495 Introduction to Computer Vision 8C-L3 Support Vector Machines Discriminative classifiers Discriminative classifiers find a division (surface) in feature space that separates the classes Several
More informationVery Deep Residual Networks with Maxout for Plant Identification in the Wild Milan Šulc, Dmytro Mishkin, Jiří Matas
Very Deep Residual Networks with Maxout for Plant Identification in the Wild Milan Šulc, Dmytro Mishkin, Jiří Matas Center for Machine Perception Department of Cybernetics Faculty of Electrical Engineering
More informationLinear classifiers: Logistic regression
Linear classifiers: Logistic regression STAT/CSE 416: Machine Learning Emily Fox University of Washington April 19, 2018 How confident is your prediction? The sushi & everything else were awesome! The
More informationarxiv: v1 [cs.lg] 25 Jul 2017
Partial Transfer Learning with Selective Adversarial Networks arxiv:177.791v1 [cs.lg] 25 Jul 17 Zhangjie Cao, Mingsheng Long, Jianmin Wang, and Michael I. Jordan KLiss, MOE; TNList; School of Software,
More informationCS 229 Project Final Report: Reinforcement Learning for Neural Network Architecture Category : Theory & Reinforcement Learning
CS 229 Project Final Report: Reinforcement Learning for Neural Network Architecture Category : Theory & Reinforcement Learning Lei Lei Ruoxuan Xiong December 16, 2017 1 Introduction Deep Neural Network
More informationLecture 10: Support Vector Machine and Large Margin Classifier
Lecture 10: Support Vector Machine and Large Margin Classifier Applied Multivariate Analysis Math 570, Fall 2014 Xingye Qiao Department of Mathematical Sciences Binghamton University E-mail: qiao@math.binghamton.edu
More informationHeadNet: Pedestrian Head Detection Utilizing Body in Context
HeadNet: Pedestrian Head Detection Utilizing Body in Context Gang Chen 1,2, Xufen Cai 1, Hu Han,1, Shiguang Shan 1,2,3 and Xilin Chen 1,2 1 Key Laboratory of Intelligent Information Processing of Chinese
More informationMachine learning - HT Maximum Likelihood
Machine learning - HT 2016 3. Maximum Likelihood Varun Kanade University of Oxford January 27, 2016 Outline Probabilistic Framework Formulate linear regression in the language of probability Introduce
More informationSVMC An introduction to Support Vector Machines Classification
SVMC An introduction to Support Vector Machines Classification 6.783, Biomedical Decision Support Lorenzo Rosasco (lrosasco@mit.edu) Department of Brain and Cognitive Science MIT A typical problem We have
More informationInterpreting Deep Classifiers
Ruprecht-Karls-University Heidelberg Faculty of Mathematics and Computer Science Seminar: Explainable Machine Learning Interpreting Deep Classifiers by Visual Distillation of Dark Knowledge Author: Daniela
More informationQuantum Convolutional Neural Networks
Quantum Convolutional Neural Networks Iris Cong Soonwon Choi Mikhail D. Lukin arxiv:1810.03787 Berkeley Quantum Information Seminar October 16 th, 2018 Why quantum machine learning? Machine learning: interpret
More informationNatural Language Processing
Natural Language Processing Info 59/259 Lecture 4: Text classification 3 (Sept 5, 207) David Bamman, UC Berkeley . https://www.forbes.com/sites/kevinmurnane/206/04/0/what-is-deep-learning-and-how-is-it-useful
More informationBased on the original slides of Hung-yi Lee
Based on the original slides of Hung-yi Lee Google Trends Deep learning obtains many exciting results. Can contribute to new Smart Services in the Context of the Internet of Things (IoT). IoT Services
More informationMachine Learning Basics Lecture 7: Multiclass Classification. Princeton University COS 495 Instructor: Yingyu Liang
Machine Learning Basics Lecture 7: Multiclass Classification Princeton University COS 495 Instructor: Yingyu Liang Example: image classification indoor Indoor outdoor Example: image classification (multiclass)
More informationWhat Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 Multi-layer networks Steve Renals Machine Learning Practical MLP Lecture 3 7 October 2015 MLP Lecture 3 Multi-layer networks 2 What Do Single
More informationAspect Term Extraction with History Attention and Selective Transformation 1
Aspect Term Extraction with History Attention and Selective Transformation 1 Xin Li 1, Lidong Bing 2, Piji Li 1, Wai Lam 1, Zhimou Yang 3 Presenter: Lin Ma 2 1 The Chinese University of Hong Kong 2 Tencent
More informationLearning with multiple models. Boosting.
CS 2750 Machine Learning Lecture 21 Learning with multiple models. Boosting. Milos Hauskrecht milos@cs.pitt.edu 5329 Sennott Square Learning with multiple models: Approach 2 Approach 2: use multiple models
More informationEncoder Based Lifelong Learning - Supplementary materials
Encoder Based Lifelong Learning - Supplementary materials Amal Rannen Rahaf Aljundi Mathew B. Blaschko Tinne Tuytelaars KU Leuven KU Leuven, ESAT-PSI, IMEC, Belgium firstname.lastname@esat.kuleuven.be
More informationSupport Vector Machine (SVM) and Kernel Methods
Support Vector Machine (SVM) and Kernel Methods CE-717: Machine Learning Sharif University of Technology Fall 2014 Soleymani Outline Margin concept Hard-Margin SVM Soft-Margin SVM Dual Problems of Hard-Margin
More informationFault prediction of power system distribution equipment based on support vector machine
Fault prediction of power system distribution equipment based on support vector machine Zhenqi Wang a, Hongyi Zhang b School of Control and Computer Engineering, North China Electric Power University,
More informationTutorial on Methods for Interpreting and Understanding Deep Neural Networks. Part 3: Applications & Discussion
Tutorial on Methods for Interpreting and Understanding Deep Neural Networks W. Samek, G. Montavon, K.-R. Müller Part 3: Applications & Discussion ICASSP 2017 Tutorial W. Samek, G. Montavon & K.-R. Müller
More informationLinear classifiers: Overfitting and regularization
Linear classifiers: Overfitting and regularization Emily Fox University of Washington January 25, 2017 Logistic regression recap 1 . Thus far, we focused on decision boundaries Score(x i ) = w 0 h 0 (x
More informationIs Robustness the Cost of Accuracy? A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
Is Robustness the Cost of Accuracy? A Comprehensive Study on the Robustness of 18 Deep Image Classification Models Dong Su 1*, Huan Zhang 2*, Hongge Chen 3, Jinfeng Yi 4, Pin-Yu Chen 1, and Yupeng Gao
More informationTowards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks
Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks Tian Li tian.li@pku.edu.cn EECS, Peking University Abstract Since laboratory experiments for exploring astrophysical
More informationMultiscale methods for neural image processing. Sohil Shah, Pallabi Ghosh, Larry S. Davis and Tom Goldstein Hao Li, Soham De, Zheng Xu, Hanan Samet
Multiscale methods for neural image processing Sohil Shah, Pallabi Ghosh, Larry S. Davis and Tom Goldstein Hao Li, Soham De, Zheng Xu, Hanan Samet A TALK IN TWO ACTS Part I: Stacked U-nets The globalization
More informationThe Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems
The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems Weinan E 1 and Bing Yu 2 arxiv:1710.00211v1 [cs.lg] 30 Sep 2017 1 The Beijing Institute of Big Data Research,
More informationAction-Decision Networks for Visual Tracking with Deep Reinforcement Learning
Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning Sangdoo Yun 1 Jongwon Choi 1 Youngjoon Yoo 2 Kimin Yun 3 and Jin Young Choi 1 1 ASRI, Dept. of Electrical and Computer Eng.,
More informationAnalyzing the Performance of Multilayer Neural Networks for Object Recognition
Analyzing the Performance of Multilayer Neural Networks for Object Recognition Pulkit Agrawal, Ross Girshick, Jitendra Malik {pulkitag,rbg,malik}@eecs.berkeley.edu University of California Berkeley Supplementary
More informationIntroduction to Support Vector Machines
Introduction to Support Vector Machines Hsuan-Tien Lin Learning Systems Group, California Institute of Technology Talk in NTU EE/CS Speech Lab, November 16, 2005 H.-T. Lin (Learning Systems Group) Introduction
More informationDeep Learning: Approximation of Functions by Composition
Deep Learning: Approximation of Functions by Composition Zuowei Shen Department of Mathematics National University of Singapore Outline 1 A brief introduction of approximation theory 2 Deep learning: approximation
More informationBinary Convolutional Neural Network on RRAM
Binary Convolutional Neural Network on RRAM Tianqi Tang, Lixue Xia, Boxun Li, Yu Wang, Huazhong Yang Dept. of E.E, Tsinghua National Laboratory for Information Science and Technology (TNList) Tsinghua
More informationIntroduction to Deep Neural Networks
Introduction to Deep Neural Networks Presenter: Chunyuan Li Pattern Classification and Recognition (ECE 681.01) Duke University April, 2016 Outline 1 Background and Preliminaries Why DNNs? Model: Logistic
More informationStatistical Machine Learning Theory. From Multi-class Classification to Structured Output Prediction. Hisashi Kashima.
http://goo.gl/xilnmn Course website KYOTO UNIVERSITY Statistical Machine Learning Theory From Multi-class Classification to Structured Output Prediction Hisashi Kashima kashima@i.kyoto-u.ac.jp DEPARTMENT
More informationSpatial Transformer Networks
BIL722 - Deep Learning for Computer Vision Spatial Transformer Networks Max Jaderberg Andrew Zisserman Karen Simonyan Koray Kavukcuoglu Contents Introduction to Spatial Transformers Related Works Spatial
More informationDistributed Estimation, Information Loss and Exponential Families. Qiang Liu Department of Computer Science Dartmouth College
Distributed Estimation, Information Loss and Exponential Families Qiang Liu Department of Computer Science Dartmouth College Statistical Learning / Estimation Learning generative models from data Topic
More informationCS798: Selected topics in Machine Learning
CS798: Selected topics in Machine Learning Support Vector Machine Jakramate Bootkrajang Department of Computer Science Chiang Mai University Jakramate Bootkrajang CS798: Selected topics in Machine Learning
More informationwith Local Dependencies
CS11-747 Neural Networks for NLP Structured Prediction with Local Dependencies Xuezhe Ma (Max) Site https://phontron.com/class/nn4nlp2017/ An Example Structured Prediction Problem: Sequence Labeling Sequence
More informationTime Series Data Cleaning
Time Series Data Cleaning Shaoxu Song http://ise.thss.tsinghua.edu.cn/sxsong/ Dirty Time Series Data Unreliable Readings Sensor monitoring GPS trajectory J. Freire, A. Bessa, F. Chirigati, H. T. Vo, K.
More informationJoint distribution optimal transportation for domain adaptation
Optimal Transport for Domain Adaptation (TPAMI 2016) Joint distribution optimal transportation for domain adaptation (NIPS 2017) Joint distribution optimal transportation for domain adaptation Nicolas
More informationINF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018
Machine learning for image classification Lecture 14: Reinforcement learning May 9, 2018 Page 3 Outline Motivation Introduction to reinforcement learning (RL) Value function based methods (Q-learning)
More informationLarge-Margin Thresholded Ensembles for Ordinal Regression
Large-Margin Thresholded Ensembles for Ordinal Regression Hsuan-Tien Lin and Ling Li Learning Systems Group, California Institute of Technology, U.S.A. Conf. on Algorithmic Learning Theory, October 9,
More informationLarge-Margin Thresholded Ensembles for Ordinal Regression
Large-Margin Thresholded Ensembles for Ordinal Regression Hsuan-Tien Lin (accepted by ALT 06, joint work with Ling Li) Learning Systems Group, Caltech Workshop Talk in MLSS 2006, Taipei, Taiwan, 07/25/2006
More informationParaGraphE: A Library for Parallel Knowledge Graph Embedding
ParaGraphE: A Library for Parallel Knowledge Graph Embedding Xiao-Fan Niu, Wu-Jun Li National Key Laboratory for Novel Software Technology Department of Computer Science and Technology, Nanjing University,
More informationSupplementary Material for Superpixel Sampling Networks
Supplementary Material for Superpixel Sampling Networks Varun Jampani 1, Deqing Sun 1, Ming-Yu Liu 1, Ming-Hsuan Yang 1,2, Jan Kautz 1 1 NVIDIA 2 UC Merced {vjampani,deqings,mingyul,jkautz}@nvidia.com,
More informationEfficient DNN Neuron Pruning by Minimizing Layer-wise Nonlinear Reconstruction Error
Efficient DNN Neuron Pruning by Minimizing Layer-wise Nonlinear Reconstruction Error Chunhui Jiang, Guiying Li, Chao Qian, Ke Tang Anhui Province Key Lab of Big Data Analysis and Application, University
More informationZero-Shot Learning via Class-Conditioned Deep Generative Models
Zero-Shot Learning via Class-Conditioned Deep Generative Models Wenlin Wang Joint with Yunchen Pu, Vinay Kumar Verma, Kai Fan, Yizhe Zhang, Changyou Chen, Piyush Rai, Lawrence Carin Duke University, IIT
More informationMultiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis
Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis Minghang Zhao, Myeongsu Kang, Baoping Tang, Michael Pecht 1 Backgrounds Accurate fault diagnosis is important to ensure
More informationRegML 2018 Class 8 Deep learning
RegML 2018 Class 8 Deep learning Lorenzo Rosasco UNIGE-MIT-IIT June 18, 2018 Supervised vs unsupervised learning? So far we have been thinking of learning schemes made in two steps f(x) = w, Φ(x) F, x
More informationSUPPORT VECTOR MACHINE
SUPPORT VECTOR MACHINE Mainly based on https://nlp.stanford.edu/ir-book/pdf/15svm.pdf 1 Overview SVM is a huge topic Integration of MMDS, IIR, and Andrew Moore s slides here Our foci: Geometric intuition
More informationMitosis Detection in Breast Cancer Histology Images with Multi Column Deep Neural Networks
Mitosis Detection in Breast Cancer Histology Images with Multi Column Deep Neural Networks IDSIA, Lugano, Switzerland dan.ciresan@gmail.com Dan C. Cireşan and Alessandro Giusti DNN for Visual Pattern Recognition
More informationArtificial Intelligence
Artificial Intelligence Explainable AI Marc Toussaint University of Stuttgart Winter 2018/19 Explainable AI General Concept of Explaination Data, Objective, Method, & Input Counterfactuals & Pearl Fitting
More informationMultiple Similarities Based Kernel Subspace Learning for Image Classification
Multiple Similarities Based Kernel Subspace Learning for Image Classification Wang Yan, Qingshan Liu, Hanqing Lu, and Songde Ma National Laboratory of Pattern Recognition, Institute of Automation, Chinese
More information2. Preliminaries. 3. Additive Margin Softmax Definition
Additive Margin Softmax for Face Verification Feng Wang UESTC feng.wff@gmail.com Weiyang Liu Georgia Tech wyliu@gatech.edu Haijun Liu UESTC haijun liu@126.com Jian Cheng UESTC chengjian@uestc.edu.cn Abstract
More informationMIRA, SVM, k-nn. Lirong Xia
MIRA, SVM, k-nn Lirong Xia Linear Classifiers (perceptrons) Inputs are feature values Each feature has a weight Sum is the activation activation w If the activation is: Positive: output +1 Negative, output
More informationSupport Vector Machine (SVM) and Kernel Methods
Support Vector Machine (SVM) and Kernel Methods CE-717: Machine Learning Sharif University of Technology Fall 2015 Soleymani Outline Margin concept Hard-Margin SVM Soft-Margin SVM Dual Problems of Hard-Margin
More informationDeep Learning for Precipitation Nowcasting: A Benchmark and A New Model
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model Xingjian Shi 1 Zhihan Gao 1 Leonard Lausen 1 Hao Wang 1 Dit-Yan Yeung 1 Wai-kin Wong 2 Wang-chun Woo 2 1 Department of Computer Science
More informationMachine Learning. Classification, Discriminative learning. Marc Toussaint University of Stuttgart Summer 2015
Machine Learning Classification, Discriminative learning Structured output, structured input, discriminative function, joint input-output features, Likelihood Maximization, Logistic regression, binary
More informationDo Neural Network Cross-Modal Mappings Really Bridge Modalities?
Do Neural Network Cross-Modal Mappings Really Bridge Modalities? Language Intelligence and Information Retrieval group (LIIR) Department of Computer Science Story Collell, G., Zhang, T., Moens, M.F. (2017)
More informationClassification Based on Logical Concept Analysis
Classification Based on Logical Concept Analysis Yan Zhao and Yiyu Yao Department of Computer Science, University of Regina, Regina, Saskatchewan, Canada S4S 0A2 E-mail: {yanzhao, yyao}@cs.uregina.ca Abstract.
More informationMaking Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation
Making Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation Dr. Yanjun Qi Department of Computer Science University of Virginia Tutorial @ ACM BCB-2018 8/29/18 Yanjun Qi / UVA
More informationAxiomatic Attribution of Neural Networks
Axiomatic Attribution of Neural Networks Mukund Sundararajan* 1, Ankur Taly* 1, Qiqi Yan* 1 1 Google Inc. Presenter: Arshdeep Sekhon Mukund Sundararajan*, Ankur Taly*, Qiqi Yan*Axiomatic Attribution of
More informationCSCI-567: Machine Learning (Spring 2019)
CSCI-567: Machine Learning (Spring 2019) Prof. Victor Adamchik U of Southern California Mar. 19, 2019 March 19, 2019 1 / 43 Administration March 19, 2019 2 / 43 Administration TA3 is due this week March
More informationIntroduction to Machine Learning Lecture 13. Mehryar Mohri Courant Institute and Google Research
Introduction to Machine Learning Lecture 13 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Multi-Class Classification Mehryar Mohri - Introduction to Machine Learning page 2 Motivation
More informationPRUNING CONVOLUTIONAL NEURAL NETWORKS. Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila Jan Kautz
PRUNING CONVOLUTIONAL NEURAL NETWORKS Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila Jan Kautz 2017 WHY WE CAN PRUNE CNNS? 2 WHY WE CAN PRUNE CNNS? Optimization failures : Some neurons are "dead":
More informationQuantifying Fingerprint Evidence using Bayesian Alignment
Quantifying Fingerprint Evidence using Bayesian Alignment Peter Forbes Joint work with Steffen Lauritzen and Jesper Møller Department of Statistics University of Oxford UCL CSML Lunch Talk 14 February
More informationLinear vs Non-linear classifier. CS789: Machine Learning and Neural Network. Introduction
Linear vs Non-linear classifier CS789: Machine Learning and Neural Network Support Vector Machine Jakramate Bootkrajang Department of Computer Science Chiang Mai University Linear classifier is in the
More informationCOMPLEX INPUT CONVOLUTIONAL NEURAL NETWORKS FOR WIDE ANGLE SAR ATR
COMPLEX INPUT CONVOLUTIONAL NEURAL NETWORKS FOR WIDE ANGLE SAR ATR Michael Wilmanski #*1, Chris Kreucher *2, & Alfred Hero #3 # University of Michigan 500 S State St, Ann Arbor, MI 48109 1 wilmansk@umich.edu,
More informationHou, Ch. et al. IEEE Transactions on Neural Networks March 2011
Hou, Ch. et al. IEEE Transactions on Neural Networks March 2011 Semi-supervised approach which attempts to incorporate partial information from unlabeled data points Semi-supervised approach which attempts
More informationDeep Residual. Variations
Deep Residual Network and Its Variations Diyu Yang (Originally prepared by Kaiming He from Microsoft Research) Advantages of Depth Degradation Problem Possible Causes? Vanishing/Exploding Gradients. Overfitting
More informationCS145: INTRODUCTION TO DATA MINING
CS145: INTRODUCTION TO DATA MINING 5: Vector Data: Support Vector Machine Instructor: Yizhou Sun yzsun@cs.ucla.edu October 18, 2017 Homework 1 Announcements Due end of the day of this Thursday (11:59pm)
More informationRecurrent Autoregressive Networks for Online Multi-Object Tracking. Presented By: Ishan Gupta
Recurrent Autoregressive Networks for Online Multi-Object Tracking Presented By: Ishan Gupta Outline Multi Object Tracking Recurrent Autoregressive Networks (RANs) RANs for Online Tracking Other State
More informationMachine Learning Basics Lecture 2: Linear Classification. Princeton University COS 495 Instructor: Yingyu Liang
Machine Learning Basics Lecture 2: Linear Classification Princeton University COS 495 Instructor: Yingyu Liang Review: machine learning basics Math formulation Given training data x i, y i : 1 i n i.i.d.
More informationParallel and Distributed Stochastic Learning -Towards Scalable Learning for Big Data Intelligence
Parallel and Distributed Stochastic Learning -Towards Scalable Learning for Big Data Intelligence oé LAMDA Group H ŒÆOŽÅ Æ EâX ^ #EâI[ : liwujun@nju.edu.cn Dec 10, 2016 Wu-Jun Li (http://cs.nju.edu.cn/lwj)
More informationJuergen Gall. Analyzing Human Behavior in Video Sequences
Juergen Gall Analyzing Human Behavior in Video Sequences 09. 10. 2 01 7 Juer gen Gall Instit u t e of Com puter Science III Com puter Vision Gr oup 2 Analyzing Human Behavior Analyzing Human Behavior Human
More informationAn EoS-meter of QCD transition from deep learning
An EoS-meter of QCD transition from deep learning Nan Su Frankfurt Institute for Advanced Studies with Long-Gang Pang, Kai Zhou (FIAS), Hannah Petersen, Horst Stöcker (FIAS/Uni Frankfurt/GSI), Xin-Nian
More informationSpatial Transformer. Ref: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, Spatial Transformer Networks, NIPS, 2015
Spatial Transormer Re: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, Spatial Transormer Networks, NIPS, 2015 Spatial Transormer Layer CNN is not invariant to scaling and rotation
More information