MIL-UT at ILSVRC2014

Size: px
Start display at page:

Download "MIL-UT at ILSVRC2014"

Transcription

1 MIL-UT at ILSVRC2014 IIT Guwahati (undergrad) -> Virginia Tech (intern) Senthil Purushwalkam, Yuichiro Tsuchiya, Atsushi Kanehira, Asako Kanezaki and *Tatsuya Harada The University of Tokyo

2 Pipeline of CLS-LOC task 1-1 Scoring each bounding boxes by RCNN Multiclass Object Detection with hard negative classes Input image Extract region proposals Extract CNN features fc7 1-2 Scoring whole image by FV as contextual scores with hard negative mining Scoring regions by Late fusion Score Whole image Extract FV with spacial information Scoring whole image by

3 Region Proposals and Feature Extraction 1-1 Scoring each bounding boxes by RCNN Input image Extract region proposals Extract CNN features fc7 with hard negative mining Scoring regions by 1-2 Scoring whole image by FV as contextual scores Late fusion Score Whole image Extract FV with spacial information Scoring whole image by R-CNN R. Girshick, J. Donahue, T. Darrell, J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR, Region proposals Selective Search J.R.R. Uijlings, K.E.A. van de Sande, T. Gevers, A.W.M. Smeulders. Selective Search for Object Recognition. IJCV, CNN features Single CNN model (5 conv layers, 2 fully connected layers) Pre-computed ILSVRC13 model No fine-tuning 4096 dim fc7 features

4 Multiclass Object Detection 1-1 Scoring each bounding boxes by RCNN Input image Extract region proposals Extract CNN features fc7 with hard negative mining Scoring regions by 1-2 Scoring whole image by FV as contextual scores Late fusion Score Whole image Extract FV with spacial information Scoring whole image by Hard negatives classes Idea: Create negative classes and train on 2K classes A. Kanezaki, S. Inaba, Y. Ushiku, Y. Yamashita, H. Muraoka, Y. Kuniyoshi and T. Harada. Hard Negative Classes for Multiple Object Detection. ICRA, Minimize detection errors as well as classification errors algorithm with hard negative mining

5 Multiclass object detection (training with negative classes) We use (PA) [Crammer et al., 2006] W t+1 = arg min W 1 to learn multi-class linear classifiers. 2 W W t 2 + Cζs. t. l x i t, y i t ; W ζ, ζ 0 ERROR Wx t = w K x t = Score of class 1 Score of class 2 Score of class K r s : Positive class : Negative class with the highest score w r (t+1) = wr (t) + τt x t w s (t+1) = ws (t) τt x t where τ t = min C, 1 (w t T t r x t w T s x t ) 2 x 2 t

6 Multiclass object detection (training with negative classes) Core Idea Hard negative classes l x i t, y i t ; W ERROR w 1 w 2 w K w K x t = Score of class 1 Score of class 2 Score of class K w 1 w 2 Score of negative class 1 Score of negative class 2 Score of negative class K Cf.) single background class w bg does not work. w r (t+1) = wr (t) + τt x t w s (t+1) = ws (t) τt x t where τ t = min C, 1 (w t T t r x t w T s x t ) 2 x 2 t

7 Multiclass object detection (training with negative classes) Ex.) If a training sample x t is a positive sample of class 2, w 1 w 2 w K x t = Score of class 1 Score of class 2 Score of class K w 1 w 2 Score of negative class 1 Score of negative class 2 w K Score of negative class K l x i t, y i t ; W ERROR r s Classification error = class 2 : Negative class with the highest score Candidates of s: class1, 3,, or K, or negative class 2 w r (t+1) = wr (t) + τt x t w s (t+1) = ws (t) τt x t where τ t = min C, 1 (w t T t r x t w T s x t ) 2 x 2 t

8 Multiclass object detection (training with negative classes) Ex.) If a training sample x t is a negative sample of class 2, w 1 w 2 w K x t = Score of class 1 Score of class 2 Score of class K w 1 w 2 Score of negative class 1 Score of negative class 2 w K Score of negative class K l x i t, y i t ; W ERROR s r Detection error = class 2 = negative class 2 w r (t+1) = wr (t) + τt x t w s (t+1) = ws (t) τt x t where τ t = min C, 1 (w t T t r x t w T s x t ) 2 x 2 t

9 Features for Contextual Scores 1-1 Scoring each bounding boxes by RCNN Input image Extract region proposals Extract CNN features fc7 with hard negative mining Scoring regions by 1-2 Scoring whole image by FV as contextual scores Late fusion Score Whole image Extract FV with spacial information Scoring whole image by Improved Fisher Vector F. Perronnin, J. Sanchez, and T. Mensink. Improving the fisher kernel for large-scale image classification. ECCV, INRIA's Fisher vector implementation L2 normalization, Power normalization, Spatial pyramid Parameters of IFV for all local features in our system Dimension reduction of local feature (D): 64 dim # of components in GMM (K): scales of local patches Spatial pyramid (P): 1x1 + 2x2 + 3x1 = 8 Dimension of IFK: 2PKD=262,144 dim Local Descriptors SIFT 9

10 Classifiers for Contextual Scores 1-1 Scoring each bounding boxes by RCNN Input image Extract region proposals Extract CNN features fc7 with hard negative mining Scoring regions by 1-2 Scoring whole image by FV as contextual scores Late fusion Score Whole image Extract FV with spacial information Scoring whole image by 10

11 Online Learning for Large-Scale Visual Recognition Three guidelines Y. Ushiku, M. Hidaka, T. Harada. Three Guidelines of Online Learning for Large-Scale Visual Recognition. CVPR, Perceptron can compete against the latest methods. Provided that the second guideline is observed. 2. Averaging is necessary for any algorithm. First-order algorithms w/o averaging cannot compete against second-order algorithms. When averaging is used, the accuracies of all algorithms become very close to each other. 3. Investigate multiclass learning first. Both one-versus-the-rest learning and multiclass learning achieve similar accuracy. However, one-versus-the-rest takes much longer CPU time to converge than multiclass does. y i Averaging arg max μ x y Y \ y 1 μ T i μ 1 y i μ 2 i μ T

12 Late Fusion Input image 1-1 Scoring each bounding boxes by RCNN Extract region proposals Compute CNN features fc7 Multiclass PA for class 1 Multiclass PA for class j Multiclass PA for class 1000 Scoring regions by Multiclass PA for each class CNN S i,1 CNN S i,j CNN S i, Scoring whole image by FV as contextual scores Whole image Extract FV with spacial information 2. Rescoring with combining RCNN feature and FV Multiclass PA for class 1 Multiclass PA for class j Multiclass PA for class 1000 Scoring by linear classifier trained by PA for each class S 1 FV S j FV FV S 1000 For bounding box i, class j, S new i,j = S CNN FV i,j S j

13 Results Method Localization error Classification error R-CNN feature + one-vs-all SVMs R-CNN feature + multi-class PA R-CNN feature + multi-class PA using hard negative classes Validation dataset R-CNN feature + multi-class PA using hard negative classes, and FV Test dataset Team name Localization error Classification error VGG GoogLeNet SYSU_Vision MIL (our team)

14 Conclusion 1-1 Scoring each bounding boxes by RCNN Input image Extract region proposals Extract CNN features fc7 1-2 Scoring whole image by FV as contextual scores with hard negative mining Scoring regions by Late fusion Score Whole image Extract FV with spacial information Scoring whole image by Our pipeline R-CNN based region proposals and features with multi-class object detectors which create hard negative class for each positive class Global features (FVs) with multi-class online-learning Late fusion of region score and global score Combining R-CNN with the contextual information improves the localization performance. Multi-class object detector trained with hard negative classes outperforms one-vs.- the-rest SVMs.

CS230: Lecture 5 Advanced topics in Object Detection

CS230: Lecture 5 Advanced topics in Object Detection CS230: Lecture 5 Advanced topics in Object Detection Stanford University Today s outline We will learn: - the Intuition behind object detection methods - a series of computer vision papers I. Object detection

More information

Compressed Fisher vectors for LSVR

Compressed Fisher vectors for LSVR XRCE@ILSVRC2011 Compressed Fisher vectors for LSVR Florent Perronnin and Jorge Sánchez* Xerox Research Centre Europe (XRCE) *Now with CIII, Cordoba University, Argentina Our system in a nutshell High-dimensional

More information

Fisher Vector image representation

Fisher Vector image representation Fisher Vector image representation Machine Learning and Category Representation 2014-2015 Jakob Verbeek, January 9, 2015 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.14.15 A brief recap on kernel

More information

Fine-grained Classification

Fine-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 information

Asaf Bar Zvi Adi Hayat. Semantic Segmentation

Asaf 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 information

Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery

Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery Aruni RoyChowdhury Synthesis Project Report College of Information and Computer Sciences University of Massachusetts, Amherst

More information

Representing Sets of Instances for Visual Recognition

Representing Sets of Instances for Visual Recognition Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) Representing Sets of Instances for Visual Recognition Jianxin Wu, 1 Bin-Bin Gao, 1 Guoqing Liu 2 1 National Key Laboratory

More information

HeadNet: Pedestrian Head Detection Utilizing Body in Context

HeadNet: 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 information

Very 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 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 information

Higher-order Statistical Modeling based Deep CNNs (Part-I)

Higher-order Statistical Modeling based Deep CNNs (Part-I) Higher-order Statistical Modeling based Deep CNNs (Part-I) Classical Methods & From Shallow to Deep Qilong Wang 2018-11-23 Context 1 2 3 4 Higher-order Statistics in Bag-of-Visual-Words (BoVW) Higher-order

More information

arxiv: v2 [cs.cv] 15 Jul 2018

arxiv: v2 [cs.cv] 15 Jul 2018 Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation arxiv:17.07321v2 [cs.cv] 15 Jul 2018 Gui-Song Xia 1, Xin-Yi Tong 1, Fan Hu 2, Yanfei Zhong 1, Mihai Datcu 3, Liangpei

More information

arxiv: v1 [cs.cv] 11 May 2015 Abstract

arxiv: 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 information

Anticipating Visual Representations from Unlabeled Data. Carl Vondrick, Hamed Pirsiavash, Antonio Torralba

Anticipating Visual Representations from Unlabeled Data. Carl Vondrick, Hamed Pirsiavash, Antonio Torralba Anticipating Visual Representations from Unlabeled Data Carl Vondrick, Hamed Pirsiavash, Antonio Torralba Overview Problem Key Insight Methods Experiments Problem: Predict future actions and objects Image

More information

TRAFFIC SCENE RECOGNITION BASED ON DEEP CNN AND VLAD SPATIAL PYRAMIDS

TRAFFIC SCENE RECOGNITION BASED ON DEEP CNN AND VLAD SPATIAL PYRAMIDS TRAFFIC SCENE RECOGNITION BASED ON DEEP CNN AND VLAD SPATIAL PYRAMIDS FANG-YU WU 1, SHI-YANG YAN 1, JEREMY S. SMITH 2, BAI-LING ZHANG 1 1 Department of Computer Science and Software Engineering, Xi an

More information

38 1 Vol. 38, No ACTA AUTOMATICA SINICA January, Bag-of-phrases.. Image Representation Using Bag-of-phrases

38 1 Vol. 38, No ACTA AUTOMATICA SINICA January, Bag-of-phrases.. Image Representation Using Bag-of-phrases 38 1 Vol. 38, No. 1 2012 1 ACTA AUTOMATICA SINICA January, 2012 Bag-of-phrases 1, 2 1 1 1, Bag-of-words,,, Bag-of-words, Bag-of-phrases, Bag-of-words DOI,, Bag-of-words, Bag-of-phrases, SIFT 10.3724/SP.J.1004.2012.00046

More information

Toward Correlating and Solving Abstract Tasks Using Convolutional Neural Networks Supplementary Material

Toward 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 information

Urban land use information retrieval based on scene classification of Google Street View images

Urban land use information retrieval based on scene classification of Google Street View images Urban land use information retrieval based on scene classification of Google Street View images Xiaojiang Li 1, Chuanrong Zhang 1 1 Department of Geography, University of Connecticut, Storrs Email: {xiaojiang.li;chuanrong.zhang}@uconn.edu

More information

Beyond Spatial Pyramids

Beyond Spatial Pyramids Beyond Spatial Pyramids Receptive Field Learning for Pooled Image Features Yangqing Jia 1 Chang Huang 2 Trevor Darrell 1 1 UC Berkeley EECS 2 NEC Labs America Goal coding pooling Bear Analysis of the pooling

More information

Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery

Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery Aruni RoyChowdhury Daniel Sheldon Subhransu Maji Erik Learned-Miller University of Massachusetts, Amherst {arunirc,sheldon,smaji,elm}@cs.umass.edu

More information

Support vector machines Lecture 4

Support vector machines Lecture 4 Support vector machines Lecture 4 David Sontag New York University Slides adapted from Luke Zettlemoyer, Vibhav Gogate, and Carlos Guestrin Q: What does the Perceptron mistake bound tell us? Theorem: The

More information

The state of the art and beyond

The state of the art and beyond Feature Detectors and Descriptors The state of the art and beyond Local covariant detectors and descriptors have been successful in many applications Registration Stereo vision Motion estimation Matching

More information

Convolutional Neural Network Architecture

Convolutional Neural Network Architecture Convolutional Neural Network Architecture Zhisheng Zhong Feburary 2nd, 2018 Zhisheng Zhong Convolutional Neural Network Architecture Feburary 2nd, 2018 1 / 55 Outline 1 Introduction of Convolution Motivation

More information

arxiv: v1 [cs.cv] 24 Nov 2017

arxiv: v1 [cs.cv] 24 Nov 2017 Feature Selective Network Feature Selective Networks for Object Detection Yao Zhai 1, Jingjing Fu 2, Yan Lu 2, and Houqiang Li 1 1 University of Science and Technology of China 2 Microsoft Research Asia

More information

FACTORIZATION MACHINES AS A TOOL FOR HEALTHCARE CASE STUDY ON TYPE 2 DIABETES DETECTION

FACTORIZATION MACHINES AS A TOOL FOR HEALTHCARE CASE STUDY ON TYPE 2 DIABETES DETECTION SunLab Enlighten the World FACTORIZATION MACHINES AS A TOOL FOR HEALTHCARE CASE STUDY ON TYPE 2 DIABETES DETECTION Ioakeim (Kimis) Perros and Jimeng Sun perros@gatech.edu, jsun@cc.gatech.edu COMPUTATIONAL

More information

Analyzing the Performance of Multilayer Neural Networks for Object Recognition

Analyzing 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 information

Workshop on Web- scale Vision and Social Media ECCV 2012, Firenze, Italy October, 2012 Linearized Smooth Additive Classifiers

Workshop on Web- scale Vision and Social Media ECCV 2012, Firenze, Italy October, 2012 Linearized Smooth Additive Classifiers Worshop on Web- scale Vision and Social Media ECCV 2012, Firenze, Italy October, 2012 Linearized Smooth Additive Classifiers Subhransu Maji Research Assistant Professor Toyota Technological Institute at

More information

Learning to Rank Using Privileged Information

Learning to Rank Using Privileged Information Learning to Rank Using Privileged Information Viktoriia Sharmanska IST Austria Klosterneuburg, Austria viktoriia.sharmanska@ist.ac.at Novi Quadrianto University of Cambridge Cambridge, UK novi.quadrianto@gmail.com

More information

Binary Convolutional Neural Network on RRAM

Binary 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 information

ML4NLP Multiclass Classification

ML4NLP Multiclass Classification ML4NLP Multiclass Classification CS 590NLP Dan Goldwasser Purdue University dgoldwas@purdue.edu Social NLP Last week we discussed the speed-dates paper. Interesting perspective on NLP problems- Can we

More information

Deep Scene Image Classification with the MFAFVNet

Deep Scene Image Classification with the MFAFVNet 2017 IEEE International Conference on Computer Vision Deep Scene Image Classification with the MFAFVNet Yunsheng Li Mandar Dixit Nuno Vasconcelos University of California, San Diego La Jolla, CA 92093

More information

Online Passive- Aggressive Algorithms

Online Passive- Aggressive Algorithms Online Passive- Aggressive Algorithms Jean-Baptiste Behuet 28/11/2007 Tutor: Eneldo Loza Mencía Seminar aus Maschinellem Lernen WS07/08 Overview Online algorithms Online Binary Classification Problem Perceptron

More information

OBJECT DETECTION FROM MMS IMAGERY USING DEEP LEARNING FOR GENERATION OF ROAD ORTHOPHOTOS

OBJECT DETECTION FROM MMS IMAGERY USING DEEP LEARNING FOR GENERATION OF ROAD ORTHOPHOTOS OBJECT DETECTION FROM MMS IMAGERY USING DEEP LEARNING FOR GENERATION OF ROAD ORTHOPHOTOS Y. Li 1,*, M. Sakamoto 1, T. Shinohara 1, T. Satoh 1 1 PASCO CORPORATION, 2-8-10 Higashiyama, Meguro-ku, Tokyo 153-0043,

More information

Lecture 13 Visual recognition

Lecture 13 Visual recognition Lecture 13 Visual recognition Announcements Silvio Savarese Lecture 13-20-Feb-14 Lecture 13 Visual recognition Object classification bag of words models Discriminative methods Generative methods Object

More information

Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time

Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time Experiment presentation for CS3710:Visual Recognition Presenter: Zitao Liu University of Pittsburgh ztliu@cs.pitt.edu

More information

Domain adaptation for deep learning

Domain 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 information

Tutorial on Methods for Interpreting and Understanding Deep Neural Networks. Part 3: Applications & Discussion

Tutorial 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 information

Fantope Regularization in Metric Learning

Fantope Regularization in Metric Learning Fantope Regularization in Metric Learning CVPR 2014 Marc T. Law (LIP6, UPMC), Nicolas Thome (LIP6 - UPMC Sorbonne Universités), Matthieu Cord (LIP6 - UPMC Sorbonne Universités), Paris, France Introduction

More information

Loss Functions and Optimization. Lecture 3-1

Loss Functions and Optimization. Lecture 3-1 Lecture 3: Loss Functions and Optimization Lecture 3-1 Administrative Assignment 1 is released: http://cs231n.github.io/assignments2017/assignment1/ Due Thursday April 20, 11:59pm on Canvas (Extending

More information

SELF-SUPERVISION. Nate Russell, Christian Followell, Pratik Lahiri

SELF-SUPERVISION. Nate Russell, Christian Followell, Pratik Lahiri SELF-SUPERVISION Nate Russell, Christian Followell, Pratik Lahiri TASKS Classification & Detection Segmentation Retrieval Action Prediction And Many More Strong Supervision Monarch Butterfly Monarch Butterfly

More information

FAemb: a function approximation-based embedding method for image retrieval

FAemb: a function approximation-based embedding method for image retrieval FAemb: a function approximation-based embedding method for image retrieval Thanh-Toan Do Quang D Tran Ngai-Man Cheung Singapore University of Technology and Design {thanhtoan do, quang tran, ngaiman cheung}@sutdedusg

More information

MIRA, SVM, k-nn. Lirong Xia

MIRA, 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 information

Accelerating Very Deep Convolutional Networks for Classification and Detection

Accelerating Very Deep Convolutional Networks for Classification and Detection Accelerating Very Deep Convolutional Networks for Classification and Detection Xiangyu Zhang, Jianhua Zou, Kaiming He, and Jian Sun arxiv:55.6798v [cs.cv] 6 May 5 Abstract This paper aims to accelerate

More information

Linear Models for Classification

Linear Models for Classification Linear Models for Classification Henrik I Christensen Robotics & Intelligent Machines @ GT Georgia Institute of Technology, Atlanta, GA 30332-0280 hic@cc.gatech.edu Henrik I Christensen (RIM@GT) Linear

More information

Pictorial Structures Revisited: People Detection and Articulated Pose Estimation. Department of Computer Science TU Darmstadt

Pictorial Structures Revisited: People Detection and Articulated Pose Estimation. Department of Computer Science TU Darmstadt Pictorial Structures Revisited: People Detection and Articulated Pose Estimation Mykhaylo Andriluka Stefan Roth Bernt Schiele Department of Computer Science TU Darmstadt Generic model for human detection

More information

Towards Good Practices for Action Video Encoding

Towards Good Practices for Action Video Encoding Towards Good Practices for Action Video Encoding Jianxin Wu National Key Laboratory for Novel Software Technology Nanjing University, China wujx21@nju.edu.cn Yu Zhang Nanyang Technological University Singapore

More information

Two-Stream Bidirectional Long Short-Term Memory for Mitosis Event Detection and Stage Localization in Phase-Contrast Microscopy Images

Two-Stream Bidirectional Long Short-Term Memory for Mitosis Event Detection and Stage Localization in Phase-Contrast Microscopy Images Two-Stream Bidirectional Long Short-Term Memory for Mitosis Event Detection and Stage Localization in Phase-Contrast Microscopy Images Yunxiang Mao and Zhaozheng Yin (B) Computer Science, Missouri University

More information

Kai Yu NEC Laboratories America, Cupertino, California, USA

Kai Yu NEC Laboratories America, Cupertino, California, USA Kai Yu NEC Laboratories America, Cupertino, California, USA Joint work with Jinjun Wang, Fengjun Lv, Wei Xu, Yihong Gong Xi Zhou, Jianchao Yang, Thomas Huang, Tong Zhang Chen Wu NEC Laboratories America

More information

Real Estate Price Prediction with Regression and Classification CS 229 Autumn 2016 Project Final Report

Real Estate Price Prediction with Regression and Classification CS 229 Autumn 2016 Project Final Report Real Estate Price Prediction with Regression and Classification CS 229 Autumn 2016 Project Final Report Hujia Yu, Jiafu Wu [hujiay, jiafuwu]@stanford.edu 1. Introduction Housing prices are an important

More information

Discriminative part-based models. Many slides based on P. Felzenszwalb

Discriminative part-based models. Many slides based on P. Felzenszwalb More sliding window detection: ti Discriminative part-based models Many slides based on P. Felzenszwalb Challenge: Generic object detection Pedestrian detection Features: Histograms of oriented gradients

More information

Flower species identification using deep convolutional neural networks

Flower species identification using deep convolutional neural networks Flower species identification using deep convolutional neural networks Thi Thanh Nhan Nguyen 1,2, Van Tuan Le 1, Thi Lan Le 1, Hai Vu 1 Natapon Pantuwong 3, Yasushi Yagi 4 1) International Research Institute

More information

Learning to Rank and Quadratic Assignment

Learning to Rank and Quadratic Assignment Learning to Rank and Quadratic Assignment Thomas Mensink TVPA - XRCE & LEAR - INRIA Grenoble, France Jakob Verbeek LEAR Team INRIA Rhône-Alpes Grenoble, France Abstract Tiberio Caetano Machine Learning

More information

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Two 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 information

Self-Adaptable Templates for Feature Coding

Self-Adaptable Templates for Feature Coding Self-Adaptable Templates for Feature Coding Xavier Boix 1,2 Gemma Roig 1,2 Salomon Diether 1 Luc Van Gool 1 1 Computer Vision Laboratory, ETH Zurich, Switzerland 2 LCSL, Massachusetts Institute of Technology

More information

Kernel Learning for Multi-modal Recognition Tasks

Kernel Learning for Multi-modal Recognition Tasks Kernel Learning for Multi-modal Recognition Tasks J. Saketha Nath CSE, IIT-B IBM Workshop J. Saketha Nath (IIT-B) IBM Workshop 23-Sep-09 1 / 15 Multi-modal Learning Tasks Multiple views or descriptions

More information

SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES

SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES Tetsu Matsukawa and Takio Kurita Department of Computer Science, University of Tsukuba, Tennodai 1-1-1 Tsukuba, Japan

More information

Midterms. PAC Learning SVM Kernels+Boost Decision Trees. MultiClass CS446 Spring 17

Midterms. PAC Learning SVM Kernels+Boost Decision Trees. MultiClass CS446 Spring 17 Midterms PAC Learning SVM Kernels+Boost Decision Trees 1 Grades are on a curve Midterms Will be available at the TA sessions this week Projects feedback has been sent. Recall that this is 25% of your grade!

More information

Statistical learning theory, Support vector machines, and Bioinformatics

Statistical learning theory, Support vector machines, and Bioinformatics 1 Statistical learning theory, Support vector machines, and Bioinformatics Jean-Philippe.Vert@mines.org Ecole des Mines de Paris Computational Biology group ENS Paris, november 25, 2003. 2 Overview 1.

More information

Deep Learning. Hung-yi Lee 李宏毅

Deep Learning. Hung-yi Lee 李宏毅 Deep Learning Hung-yi Lee 李宏毅 Deep learning attracts lots of attention. I believe you have seen lots of exciting results before. Deep learning trends at Google. Source: SIGMOD 206/Jeff Dean 958: Perceptron

More information

SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES

SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES Tetsu Matsukawa and Takio Kurita :Department of Computer Science, University of Tsukuba, Tennodai 1-1-1 Tsukuba, Japan

More information

Deep Learning (CNNs)

Deep Learning (CNNs) 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deep Learning (CNNs) Deep Learning Readings: Murphy 28 Bishop - - HTF - - Mitchell

More information

Machine learning for pervasive systems Classification in high-dimensional spaces

Machine learning for pervasive systems Classification in high-dimensional spaces Machine learning for pervasive systems Classification in high-dimensional spaces Department of Communications and Networking Aalto University, School of Electrical Engineering stephan.sigg@aalto.fi Version

More information

arxiv: v2 [cs.cv] 7 Feb 2018

arxiv: v2 [cs.cv] 7 Feb 2018 Focal Loss for Dense Object Detection Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He Piotr Dollár Facebook AI Research (FAIR) arxiv:78.v [cs.cv] 7 Feb 8 loss 5 4 3 CE(p t) = log(p t) FL(p t) = ( p t)

More information

Distinguish between different types of scenes. Matching human perception Understanding the environment

Distinguish between different types of scenes. Matching human perception Understanding the environment Scene Recognition Adriana Kovashka UTCS, PhD student Problem Statement Distinguish between different types of scenes Applications Matching human perception Understanding the environment Indexing of images

More information

Use Bin-Ratio Information for Category and Scene Classification

Use Bin-Ratio Information for Category and Scene Classification Use Bin-Ratio Information for Category and Scene Classification Nianhua Xie 1,2, Haibin Ling 2, Weiming Hu 1, Xiaoqin Zhang 1 1 National Laboratory of Pattern Recognition, Institute of Automation, CAS,

More information

Evaluation. Andrea Passerini Machine Learning. Evaluation

Evaluation. Andrea Passerini Machine Learning. Evaluation Andrea Passerini passerini@disi.unitn.it Machine Learning Basic concepts requires to define performance measures to be optimized Performance of learning algorithms cannot be evaluated on entire domain

More information

Histogram of multi-directional Gabor filter bank for motion trajectory feature extraction

Histogram of multi-directional Gabor filter bank for motion trajectory feature extraction Histogram of multi-directional Gabor filter bank for motion trajectory feature extraction NGOC NAM BUI, TAN DAT TRINH, MIN KYUNG PARK, JIN YOUNG KIM Dept. of Electronics and Computer Engineering Chonnam

More information

Evaluation requires to define performance measures to be optimized

Evaluation requires to define performance measures to be optimized Evaluation Basic concepts Evaluation requires to define performance measures to be optimized Performance of learning algorithms cannot be evaluated on entire domain (generalization error) approximation

More information

Learning Discriminative and Transformation Covariant Local Feature Detectors

Learning Discriminative and Transformation Covariant Local Feature Detectors Learning Discriminative and Transformation Covariant Local Feature Detectors Xu Zhang 1, Felix X. Yu 2, Svebor Karaman 1, Shih-Fu Chang 1 1 Columbia University, 2 Google Research {xu.zhang, svebor.karaman,

More information

Matrix Backpropagation for Deep Networks with Structured Layers

Matrix Backpropagation for Deep Networks with Structured Layers Matrix Backpropagation for Deep Networks with Structured Layers Catalin Ionescu 2,3, Orestis Vantzos 3, and Cristian Sminchisescu 1,2 1 Department of Mathematics, Faculty of Engineering, Lund University

More information

arxiv: v1 [cs.lg] 25 Jul 2017

arxiv: 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 information

Maximally Stable Local Description for Scale Selection

Maximally Stable Local Description for Scale Selection Maximally Stable Local Description for Scale Selection Gyuri Dorkó and Cordelia Schmid INRIA Rhône-Alpes, 655 Avenue de l Europe, 38334 Montbonnot, France {gyuri.dorko,cordelia.schmid}@inrialpes.fr Abstract.

More information

from Object Image Based on

from Object Image Based on Inference of Grasping Pattern from Object Image Based on Interaction Descriptor Tadashi Matsuo, Takuya Kawakami, Yoko Ogawa, Nobutaka Shimada Ritsumeikan University Introduction An object as a tool has

More information

Multi-Component Word Sense Disambiguation

Multi-Component Word Sense Disambiguation Multi-Component Word Sense Disambiguation Massimiliano Ciaramita and Mark Johnson Brown University BLLIP: http://www.cog.brown.edu/research/nlp Ciaramita and Johnson 1 Outline Pattern classification for

More information

Scale-adaptive Convolutions for Scene Parsing

Scale-adaptive Convolutions for Scene Parsing Scale-adaptive Convolutions for Scene Parsing Rui Zhang 1,3, Sheng Tang 1,3, Yongdong Zhang 1,3, Jintao Li 1,3, Shuicheng Yan 2 1 Key Laboratory of Intelligent Information Processing, Institute of Computing

More information

From Binary to Multiclass Classification. CS 6961: Structured Prediction Spring 2018

From Binary to Multiclass Classification. CS 6961: Structured Prediction Spring 2018 From Binary to Multiclass Classification CS 6961: Structured Prediction Spring 2018 1 So far: Binary Classification We have seen linear models Learning algorithms Perceptron SVM Logistic Regression Prediction

More information

Machine Learning Basics

Machine Learning Basics Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each

More information

Kronecker Decomposition for Image Classification

Kronecker Decomposition for Image Classification university of innsbruck institute of computer science intelligent and interactive systems Kronecker Decomposition for Image Classification Sabrina Fontanella 1,2, Antonio Rodríguez-Sánchez 1, Justus Piater

More information

Image Classification with the Fisher Vector: Theory and Practice

Image Classification with the Fisher Vector: Theory and Practice Image Classification with the Fisher Vector: Theory and Practice Jorge Sanchez, Florent Perronnin, Thomas Mensink, Jakob Verbeek To cite this version: Jorge Sanchez, Florent Perronnin, Thomas Mensink,

More information

A Hierarchical Convolutional Neural Network for Mitosis Detection in Phase-Contrast Microscopy Images

A Hierarchical Convolutional Neural Network for Mitosis Detection in Phase-Contrast Microscopy Images A Hierarchical Convolutional Neural Network for Mitosis Detection in Phase-Contrast Microscopy Images Yunxiang Mao and Zhaozheng Yin (B) Department of Computer Science, Missouri University of Science and

More information

DISCRIMINATIVE DECORELATION FOR CLUSTERING AND CLASSIFICATION

DISCRIMINATIVE DECORELATION FOR CLUSTERING AND CLASSIFICATION DISCRIMINATIVE DECORELATION FOR CLUSTERING AND CLASSIFICATION ECCV 12 Bharath Hariharan, Jitandra Malik, and Deva Ramanan MOTIVATION State-of-the-art Object Detection HOG Linear SVM Dalal&Triggs Histograms

More information

EE 6882 Visual Search Engine

EE 6882 Visual Search Engine EE 6882 Visual Search Engine Prof. Shih Fu Chang, Feb. 13 th 2012 Lecture #4 Local Feature Matching Bag of Word image representation: coding and pooling (Many slides from A. Efors, W. Freeman, C. Kambhamettu,

More information

A Simple Exponential Family Framework for Zero-Shot Learning

A 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 information

CS4495/6495 Introduction to Computer Vision. 8C-L3 Support Vector Machines

CS4495/6495 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 information

Warm up: risk prediction with logistic regression

Warm up: risk prediction with logistic regression Warm up: risk prediction with logistic regression Boss gives you a bunch of data on loans defaulting or not: {(x i,y i )} n i= x i 2 R d, y i 2 {, } You model the data as: P (Y = y x, w) = + exp( yw T

More information

arxiv: v4 [cs.cv] 6 Sep 2017

arxiv: v4 [cs.cv] 6 Sep 2017 Deep Pyramidal Residual Networks Dongyoon Han EE, KAIST dyhan@kaist.ac.kr Jiwhan Kim EE, KAIST jhkim89@kaist.ac.kr Junmo Kim EE, KAIST junmo.kim@kaist.ac.kr arxiv:1610.02915v4 [cs.cv] 6 Sep 2017 Abstract

More information

Reduced Memory Region Based Deep Convolutional Neural Network Detection

Reduced Memory Region Based Deep Convolutional Neural Network Detection Reduced Memory Region Based Deep Convolutional Neural Network Detection arxiv:1609.02500v1 [cs.cv] 8 Sep 2016 Denis Tomé, Luca Bondi, Luca Baroffio, Stefano Tubaro Dipartimento di Elettronica, Informazione

More information

On the road to Affine Scattering Transform

On the road to Affine Scattering Transform 1 On the road to Affine Scattering Transform Edouard Oyallon with Stéphane Mallat following the work of Laurent Sifre, Joan Bruna, High Dimensional classification (x i,y i ) 2 R 5122 {1,...,100},i=1...10

More information

A Least Squares Formulation for Canonical Correlation Analysis

A Least Squares Formulation for Canonical Correlation Analysis A Least Squares Formulation for Canonical Correlation Analysis Liang Sun, Shuiwang Ji, and Jieping Ye Department of Computer Science and Engineering Arizona State University Motivation Canonical Correlation

More information

Information Extraction from Text

Information Extraction from Text Information Extraction from Text Jing Jiang Chapter 2 from Mining Text Data (2012) Presented by Andrew Landgraf, September 13, 2013 1 What is Information Extraction? Goal is to discover structured information

More information

Jakub Hajic Artificial Intelligence Seminar I

Jakub Hajic Artificial Intelligence Seminar I Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network

More information

Deep learning attracts lots of attention.

Deep learning attracts lots of attention. Deep Learning Deep learning attracts lots of attention. I believe you have seen lots of exciting results before. Deep learning trends at Google. Source: SIGMOD/Jeff Dean Ups and downs of Deep Learning

More information

Unsupervised Domain Adaptation with Residual Transfer Networks

Unsupervised Domain Adaptation with Residual Transfer Networks Unsupervised Domain Adaptation with Residual Transfer Networks Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I. Jordan KLiss, MOE; TNList; School of Software, Tsinghua University, China University

More information

Linear smoother. ŷ = S y. where s ij = s ij (x) e.g. s ij = diag(l i (x))

Linear smoother. ŷ = S y. where s ij = s ij (x) e.g. s ij = diag(l i (x)) Linear smoother ŷ = S y where s ij = s ij (x) e.g. s ij = diag(l i (x)) 2 Online Learning: LMS and Perceptrons Partially adapted from slides by Ryan Gabbard and Mitch Marcus (and lots original slides by

More information

Self-Tuning Semantic Image Segmentation

Self-Tuning Semantic Image Segmentation Self-Tuning Semantic Image Segmentation Sergey Milyaev 1,2, Olga Barinova 2 1 Voronezh State University sergey.milyaev@gmail.com 2 Lomonosov Moscow State University obarinova@graphics.cs.msu.su Abstract.

More information

CS 1674: Intro to Computer Vision. Final Review. Prof. Adriana Kovashka University of Pittsburgh December 7, 2016

CS 1674: Intro to Computer Vision. Final Review. Prof. Adriana Kovashka University of Pittsburgh December 7, 2016 CS 1674: Intro to Computer Vision Final Review Prof. Adriana Kovashka University of Pittsburgh December 7, 2016 Final info Format: multiple-choice, true/false, fill in the blank, short answers, apply an

More information

MinOver Revisited for Incremental Support-Vector-Classification

MinOver Revisited for Incremental Support-Vector-Classification MinOver Revisited for Incremental Support-Vector-Classification Thomas Martinetz Institute for Neuro- and Bioinformatics University of Lübeck D-23538 Lübeck, Germany martinetz@informatik.uni-luebeck.de

More information

CSC321 Lecture 16: ResNets and Attention

CSC321 Lecture 16: ResNets and Attention CSC321 Lecture 16: ResNets and Attention Roger Grosse Roger Grosse CSC321 Lecture 16: ResNets and Attention 1 / 24 Overview Two topics for today: Topic 1: Deep Residual Networks (ResNets) This is the state-of-the

More information

Region Moments: Fast invariant descriptors for detecting small image structures

Region Moments: Fast invariant descriptors for detecting small image structures Region Moments: Fast invariant descriptors for detecting small image structures Gianfranco Doretto Yi Yao Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 39 doretto@research.ge.com

More information

Accelerating Convolutional Neural Networks by Group-wise 2D-filter Pruning

Accelerating Convolutional Neural Networks by Group-wise 2D-filter Pruning Accelerating Convolutional Neural Networks by Group-wise D-filter Pruning Niange Yu Department of Computer Sicence and Technology Tsinghua University Beijing 0008, China yng@mails.tsinghua.edu.cn Shi Qiu

More information

ECS289: Scalable Machine Learning

ECS289: Scalable Machine Learning ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 27, 2015 Outline One versus all/one versus one Ranking loss for multiclass/multilabel classification Scaling to millions of labels Multiclass

More information