Region Proposals. Jan Hosang, Rodrigo Benenson, Piotr Dollar, Bernt Schiele
|
|
- Jocelyn Wilcox
- 5 years ago
- Views:
Transcription
1 Region Proposals Jan Hosang, Rodrigo Benenson, Piotr Dollar, Bernt Schiele
2 Who has read a proposal paper? 2
3 Who has read a proposal paper? Who knows what Average Recall is? 2
4 Who has read a proposal paper? Who knows what Average Recall is? Who has used proposals? 2
5 Who has read a proposal paper? Who knows what Average Recall is? Who has used proposals? Who has written a paper about proposals or a paper using proposals? 2
6 Part I: Motivation & different types of proposal methods 3
7 Sliding Window Approach Slide a window and classify every location 4
8 Sliding Window Approach Slide a window and classify every location 4
9 Sliding Window Approach Slide a window and classify every location Huge search space: position x scale x aspect ratio, about Problem: classification needs to be very fast 10 6 windows 5
10 Conventional detection Image Detections with score Sliding window Classifier/Detector Discard unlikely object locations 6
11 Detection proposals: a cascaded detector Image Image & search space Detections with score Proposal method Classifier/Detector Discard unlikely object locations Discard unlikely object locations 7
12 Motivation: Efficiency Image Propose object locations Image & search space Score all proposals Detections with score Reducing search space allows slower classifiers But it comes with the cost of running a proposal method: about 0.1s 4min per image More side effects later 8
13 Approaches to propose object segments Bottom up: grouping {superpixels, pixels} into object segments Selective Search [ICCV 11, IJCV 13], Randomized Prim s [ICCV 13], [Rantalankila CVPR 14], [Chang ICCV 11], CPMC [CVPR 10, PAMI 12], [Endres ECCV 10, PAMI 14], Rigor [CVPR 14], Geodesic [ECCV 14], MCG [CVPR 14], 9
14 Grouping method example: Selective Search Used information: color similarities, texture similarities, region size, region filling Greedy merging Nothing learned 10
15 Approaches to propose object segments Bottom up: grouping {superpixels, pixels} into object segments Selective Search [ICCV 11, IJCV 13], Randomized Prim s [ICCV 13], [Rantalankila CVPR 14], [Chang ICCV 11], CPMC [CVPR 10, PAMI 12], [Endres ECCV 10, PAMI 14], Rigor [CVPR 14], Geodesic [ECCV 14], MCG [CVPR 14], Top down: hypothesize, then score a window/segment Objectness [CVPR 10, PAMI 12], [Rahtu ICCV 11], Bing [CVPR 14], EdgeBoxes [ECCV 14], [Feng ICCV 11], [Zhang CVPR 11], Randomized Seeds [ICCV 13], 11
16 Window scoring example: Edge Boxes Extract edges Group edges Extract edges Minimize the number of edges that cross the window boundary Sliding window search Refine location, scale, aspect ratio Also nothing learned 12
17 Approaches to propose object segments Bottom up: grouping {superpixels, pixels} into object segments Selective Search [ICCV 11, IJCV 13], Randomized Prim s [ICCV 13], [Rantalankila CVPR 14], [Chang ICCV 11], CPMC [CVPR 10, PAMI 12], [Endres ECCV 10, PAMI 14], Rigor [CVPR 14], Geodesic [ECCV 14], MCG [CVPR 14], Top down: hypothesize, then score a window/segment Objectness [CVPR 10, PAMI 12], [Rahtu ICCV 11], Bing [CVPR 14], EdgeBoxes [ECCV 14], [Feng ICCV 11], [Zhang CVPR 11], Randomized Seeds [ICCV 13], Miscellanea: eg. non-parametric, convnets Shape sharing [ECCV 12], Multibox [CVPR 14], DeepMask [NIPS 15], 13
18 Why are convnets different? Many methods are complexity controlled to generalize to unseen classes Simple features Simple classifier, maybe even no learning Huge VGG convnet with tens of millions of parameters? Possibility to learn n detectors inside Bigger drop in performance when generalizing to new classes But you could also count it as window scoring More on that later 14
19 Part II: Detection proposal evaluation, metrics, analysis 15
20 Detection proposals: a cascaded detector Image Image & search space Detections with score Proposal method Classifier/Detector Discard unlikely object locations Discard unlikely object locations 16
21 Detection proposals: types of mistakes Image Image & search space Detections with score false positives Proposal method Classifier/Detector false negatives 17
22 Detection proposals: types of mistakes Image Image & search space Detections with score false positives Proposal method Classifier/Detector false negatives 17
23 Detection proposals: evaluation Image Propose object locations Image & search space Score all proposals Detections with score Methods need to provide As few FNs as possible: high recall As well localized as possible: good localization As few FPs as possible: few proposals 18
24 Why do these three matter? Image Propose object locations Image & search space Score all proposals Detections with score High recall Missing recall cannot be undone Good localization Detectors give better scores for well localized windows, ie. better AP curve Few proposals This cuts down search space And reduces the number of mistakes the detector can make 19
25 Typical evaluation: fix #proposals, recall vs. IoU recall PASCAL 2007 recall better Bing CPMC EdgeBoxes Endres Geodesic MCG Objectness Rahtu RandomizedPrims Rantalankila Rigor SelectiveSearch Gaussian Sliding window Superpixels Uniform IoU overlap threshold (a) 100 proposals per image IoU overlap threshold (b) 1000proposals per image. Bing CPMC EdgeBoxes Endres Geodesic 20
26 Proposals methods are just bad detectors In the early days authors cared about class generalization In the Objectness paper [CVPR 10] set of training/test classes were disjoint Methods had either simple features or small model capacity to generalize 21
27 Proposals methods are just bad detectors In the early days authors cared about class generalization In the Objectness paper [CVPR 10] set of training/test classes were disjoint Methods had either simple features or small model capacity to generalize But on Pascal/COCO-type benchmarks Who cares about class generalization? You want high recall for few proposals At the end of the day a high recall detector is the best proposal method (e.g. Faster R-CNN) recall SquaresChnFtrs 2.8 EdgeBoxes 3.0 EdgeBoxes EdgeBoxes EdgeBoxes IoU 22
28 Proposals methods are just bad detectors In the early days authors cared about class generalization In the Objectness paper [CVPR 10] set of training/test classes were disjoint Methods had either simple features or small model capacity to generalize But on Pascal/COCO-type benchmarks Who cares about class generalization? You want high recall for few proposals At the end of the day a high recall detector is the best proposal method (e.g. Faster R-CNN) What you want to detect might not be an object (and violate the common appearance assumption ) Parts of objects: shoulder, car door, Groups of objects recall SquaresChnFtrs 2.8 EdgeBoxes 3.0 EdgeBoxes EdgeBoxes EdgeBoxes IoU 23
29 Typical evaluation: fix #proposals, recall vs. IoU recall PASCAL 2007 recall better Bing CPMC EdgeBoxes Endres Geodesic MCG Objectness Rahtu RandomizedPrims Rantalankila Rigor SelectiveSearch Gaussian Sliding window Superpixels Uniform IoU overlap threshold (a) 100 proposals per image IoU overlap threshold (b) 1000proposals per image. Bing CPMC EdgeBoxes Endres Geodesic 24
30 But how important is recall vs. localization? recall IoU overlap threshold 25
31 There is no one threshold, Better localization helps linearly detector score IoU with GT R-CNN LM-LLDA Fast R-CNN 26
32 very different mechanisms for generating proposals. ctivesearch merges superpixels, Rigor computes iple graph cut segmentations, MCG generates hierarchegmentations, Actually, and we re EdgeBoxes interested scores windows map based ge content. ralisation: Critically, we measured no significant drop call when going from the 20 PASCAL categories to the 0.9 magenet categories. Moreover, while MS COCO is subially harder and has very different 0.8 statistics (more and ler objects), relative method ordering remains mostly 1 le Experiments: The best Fast R-CNN IoU overlap results threshold reported 0.9 is paper used the large model L and EdgeBoxesAR oved0.5performance to 71.2 map, and adding an oracle 0.4 erfect non-maximum suppression further improved 0.3 to 78.1 (see 5.6 for details). The remaining gap of recall correlation with map anged. These are encouraging result 0.7 indicating that curethods do indeed generalise to different unseen categories, s such can be considered true objectness methods which is the same as the average b to reach perfect detectionminor, is caused we opted by high to use scoring AR over average the entire best o2[0.5,1.0] spatial range support from 0.5 (BSS) to 0.1 tions 1.0 for simplicity. While the strong correlation does not imply that that the arear perfectly can perfectly local- predict the closest detection proposal performance, to each ann 0on the background and object misclassifications. The ABO and BSS are typica best case analysis IoU overlap threshold for proposals as figure 13 shows, the relationship matchismore surprisingly than one linear. annotatio AR (b) proposals per image. shows that further improvement Tools for Efficient Object candetection only be Region gained Proposals by Jan Hosang 1 mask generated by many prop more important role during det progress has been rapid in this y proposal methods to evolve quic APPENDIX 60 correlation=0.961 A ANALYSIS OF METRICS map 50 Average recall (AR) between 0.5 a 40 by averaging over the overlaps o the closest 30 matched proposal, th axis 20 of the plot instead of the x ax and recall(o) the function shown Let IoU(gt i ) denote the IoU betw average recall the closest detection proposal. W (c) Fast R-CNN without bounding box regression osals, achieving map of 67.8 on PASCAL 2007 test. 0.7 ˆ1 g an oracle to rectify all localisation Figure 13: and Correlation recall errors between detector performance on P correlation between map and recall AR =2 at different recall(o)do IoU threshold = 2 nx n 0.5 = average recall(o) i=1 27
33 Trends across number of proposals average recall # proposals (c) Average recall (between IoU). Bing CPMC EdgeBoxes Endres Geodesic MCG Objectness Rahtu RandomizedPrims Rantalankila Rigor SelectiveSearch Gaussian Sliding window Superpixels Uniform 28
34 Average Recall caveat Correlates well if you don t change the number of proposals AR =2 ˆ1 0.5 recall(o)do = average o2[0.5,1.0] recall(o) But extreme cases don t look as you d expect AR # proposals mean AP EdgeBoxesAR nms oracle 53 ~ gt oracle 100 ~ both oracles 100 ~
35 Take-home messages Proposals should provide high recall and good localization with few proposals In papers present full range of operating points AR is a good summary number, but has limitations when it comparing across different number of proposals Sometimes a detector is the better proposal method If you care about few classes and don t need to generalize If the proposal methods don t work on your targets 30
36 Thanks for your attention! Questions? 31
Active Deformable Part Models Inference
Active Deformable Part Models Inference Menglong Zhu Nikolay Atanasov George J. Pappas Kostas Daniilidis GRASP Laboratory, University of Pennsylvania 3330 Walnut Street, Philadelphia, PA 19104, USA Abstract.
More informationRich feature hierarchies for accurate object detection and semantic segmentation
Rich feature hierarchies for accurate object detection and semantic segmentation Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik UC Berkeley Tech Report @ http://arxiv.org/abs/1311.2524! Detection
More informationObject Detection. Honghui Shi IBM Research Columbia
Object Detection Honghui Shi IBM Research 2018.11.27 @ Columbia Outline Problem Evaluation Methods Directions Problem Image classification: Horse (People, Dog, Truck ) Object detection: categories & locations
More informationObject-Level Saliency Detection Combining the Contrast and Spatial Compactness Hypothesis
Object-Level Saliency Detection Combining the Contrast and Spatial Compactness Hypothesis Chi Zhang 1, Weiqiang Wang 1, 2, and Xiaoqian Liu 1 1 School of Computer and Control Engineering, University of
More information2018 Keypoints Challenge
2018 Keypoints Challenge Matteo Ruggero Ronchi COCO and Mapillary Joint Visual Recognition Challenges Workshop Sunday, September 9th, Munich, Germany COCO Dataset COCO Keypoints Dataset (I) Multiple Perspectives,
More informationHierarchical Convolutional Features for Visual Tracking
Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate
More informationObjectives. Quantifying the quality of hypothesis tests. Type I and II errors. Power of a test. Cautions about significance tests
Objectives Quantifying the quality of hypothesis tests Type I and II errors Power of a test Cautions about significance tests Designing Experiments based on power Evaluating a testing procedure The testing
More informationExperiment Presentation CS Chris Thomas Experiment: What is an Object? Alexe, Bogdan, et al. CVPR 2010
Experiment Presentation CS 3710 Chris Thomas Experiment: What is an Object? Alexe, Bogdan, et al. CVPR 2010 1 Preliminaries Code for What is An Object? available online Version 2.2 Achieves near 90% recall
More informationPutting Context into. Vision. September 15, Derek Hoiem
Putting Context into Vision Derek Hoiem September 15, 2004 Questions to Answer What is context? How is context used in human vision? How is context currently used in computer vision? Conclusions Context
More informationMedical Image Analysis
Medical Image Analysis 1 Co-trained convolutional neural networks for automated detection of prostate cancer in multiparametric MRI, 2017, Medical Image Analysis 2 Graph-based prostate extraction in t2-weighted
More informationRevisiting RCNN: On Awakening the Classification Power of Faster RCNN
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN Bowen Cheng 1, Yunchao Wei 1, Honghui Shi 2, Rogerio Feris 2, Jinjun Xiong 2, and Thomas Huang 1 1 University of Illinois at Urbana-Champaign,
More informationValidating the Visual Saliency Model
Validating the Visual Saliency Model Ali Alsam and Puneet Sharma Department of Informatics & e-learning (AITeL), Sør-Trøndelag University College (HiST), Trondheim, Norway er.puneetsharma@gmail.com Abstract.
More informationTumor Cellularity Assessment. Rene Bidart
Tumor Cellularity Assessment Rene Bidart 1 Goals Find location and class of all cell nuclei: Lymphocyte Cells Normal Epithelial Cells Malignant Epithelial Cells Why: Test effectiveness of pre-surgery treatment
More informationExploiting saliency for object segmentation from image level labels
Exploiting saliency for object segmentation from image level labels Seong Joon Oh Rodrigo Benenson Anna Khoreva joon@mpi-inf.mpg.de benenson@mpi-inf.mpg.de khoreva@mpi-inf.mpg.de, Zeynep Akata Z.Akata@uva.nl
More informationLearning to Detect Salient Objects with Image-level Supervision
Learning to Detect Salient Objects with Image-level Supervision Lijun Wang 1, Huchuan Lu 1, Yifan Wang 1, Mengyang Feng 1 Dong Wang 1, Baocai Yin 1, and Xiang Ruan 2 1 Dalian University of Technology,
More informationIAT 355 Visual Analytics. Encoding Information: Design. Lyn Bartram
IAT 355 Visual Analytics Encoding Information: Design Lyn Bartram 4 stages of visualization design 2 Recall: Data Abstraction Tables Data item (row) with attributes (columns) : row=key, cells = values
More informationarxiv: v3 [cs.cv] 26 May 2018
DeepEM: Deep 3D ConvNets With EM For Weakly Supervised Pulmonary Nodule Detection Wentao Zhu, Yeeleng S. Vang, Yufang Huang, and Xiaohui Xie University of California, Irvine Lenovo AI Lab {wentaoz1,ysvang,xhx}@uci.edu,
More informationBeyond R-CNN detection: Learning to Merge Contextual Attribute
Brain Unleashing Series - Beyond R-CNN detection: Learning to Merge Contextual Attribute Shu Kong CS, ICS, UCI 2015-1-29 Outline 1. RCNN is essentially doing classification, without considering contextual
More informationAutomated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature
Automated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature Shraddha P. Dhumal 1, Ashwini S Gaikwad 2 1 Shraddha P. Dhumal 2 Ashwini S. Gaikwad ABSTRACT In this paper, we propose
More informationVisual Saliency Based on Multiscale Deep Features Supplementary Material
Visual Saliency Based on Multiscale Deep Features Supplementary Material Guanbin Li Yizhou Yu Department of Computer Science, The University of Hong Kong https://sites.google.com/site/ligb86/mdfsaliency/
More informationVideo Saliency Detection via Dynamic Consistent Spatio- Temporal Attention Modelling
AAAI -13 July 16, 2013 Video Saliency Detection via Dynamic Consistent Spatio- Temporal Attention Modelling Sheng-hua ZHONG 1, Yan LIU 1, Feifei REN 1,2, Jinghuan ZHANG 2, Tongwei REN 3 1 Department of
More informationFusing Generic Objectness and Visual Saliency for Salient Object Detection
Fusing Generic Objectness and Visual Saliency for Salient Object Detection Yasin KAVAK 06/12/2012 Citation 1: Salient Object Detection: A Benchmark Fusing for Salient Object Detection INDEX (Related Work)
More informationMEMORABILITY OF NATURAL SCENES: THE ROLE OF ATTENTION
MEMORABILITY OF NATURAL SCENES: THE ROLE OF ATTENTION Matei Mancas University of Mons - UMONS, Belgium NumediArt Institute, 31, Bd. Dolez, Mons matei.mancas@umons.ac.be Olivier Le Meur University of Rennes
More informationVISUAL search is necessary for rapid scene analysis
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 8, AUGUST 2016 3475 A Unified Framework for Salient Structure Detection by Contour-Guided Visual Search Kai-Fu Yang, Hui Li, Chao-Yi Li, and Yong-Jie
More informationEXEMPLAR BASED IMAGE SALIENT OBJECT DETECTION. {zzwang, ruihuang, lwan,
EXEMPLAR BASED IMAGE SALIENT OBJECT DETECTION Zezheng Wang Rui Huang, Liang Wan 2 Wei Feng School of Computer Science and Technology, Tianjin University, Tianjin, China 2 School of Computer Software, Tianjin
More informationAttentional Masking for Pre-trained Deep Networks
Attentional Masking for Pre-trained Deep Networks IROS 2017 Marcus Wallenberg and Per-Erik Forssén Computer Vision Laboratory Department of Electrical Engineering Linköping University 2014 2017 Per-Erik
More informationShu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge 4. Fine-grained classification with holistic representation
More informationCervical cytology intelligent diagnosis based on object detection technology
Cervical cytology intelligent diagnosis based on object detection technology Meiquan Xu xumeiquan@126.com Weixiu Zeng Semptian Co., Ltd. Machine Learning Lab. zengweixiu@gmail.com Hunhui Wu 736886978@qq.com
More informationINTRODUCTION TO MACHINE LEARNING. Decision tree learning
INTRODUCTION TO MACHINE LEARNING Decision tree learning Task of classification Automatically assign class to observations with features Observation: vector of features, with a class Automatically assign
More informationLearning Saliency Maps for Object Categorization
Learning Saliency Maps for Object Categorization Frank Moosmann, Diane Larlus, Frederic Jurie INRIA Rhône-Alpes - GRAVIR - CNRS, {Frank.Moosmann,Diane.Larlus,Frederic.Jurie}@inrialpes.de http://lear.inrialpes.fr
More informationReview. Imagine the following table being obtained as a random. Decision Test Diseased Not Diseased Positive TP FP Negative FN TN
Outline 1. Review sensitivity and specificity 2. Define an ROC curve 3. Define AUC 4. Non-parametric tests for whether or not the test is informative 5. Introduce the binormal ROC model 6. Discuss non-parametric
More informationAn Attentional Framework for 3D Object Discovery
An Attentional Framework for 3D Object Discovery Germán Martín García and Simone Frintrop Cognitive Vision Group Institute of Computer Science III University of Bonn, Germany Saliency Computation Saliency
More informationAccuracy Requirements for a Hypoglycemia Detector: An Analytical Model to Evaluate the Effects of Bias, Precision, and Rate of Glucose Change
Journal of Diabetes Science and Technology Volume 1, Issue 5, September 2007 Diabetes Technology Society SYMPOSIUM Accuracy Requirements for a Hypoglycemia Detector: An Analytical Model to Evaluate the
More informationA Hierarchical Visual Saliency Model for Character Detection in Natural Scenes
A Hierarchical Visual Saliency Model for Character Detection in Natural Scenes Renwu Gao 1(B), Faisal Shafait 2, Seiichi Uchida 3, and Yaokai Feng 3 1 Information Sciene and Electrical Engineering, Kyushu
More informationVIDEO SALIENCY INCORPORATING SPATIOTEMPORAL CUES AND UNCERTAINTY WEIGHTING
VIDEO SALIENCY INCORPORATING SPATIOTEMPORAL CUES AND UNCERTAINTY WEIGHTING Yuming Fang, Zhou Wang 2, Weisi Lin School of Computer Engineering, Nanyang Technological University, Singapore 2 Department of
More informationFlexible, High Performance Convolutional Neural Networks for Image Classification
Flexible, High Performance Convolutional Neural Networks for Image Classification Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber IDSIA, USI and SUPSI Manno-Lugano,
More informationWeek 2 Video 3. Diagnostic Metrics
Week 2 Video 3 Diagnostic Metrics Different Methods, Different Measures Today we ll continue our focus on classifiers Later this week we ll discuss regressors And other methods will get worked in later
More informationDiscovering Important People and Objects for Egocentric Video Summarization
Discovering Important People and Objects for Egocentric Video Summarization Yong Jae Lee, Joydeep Ghosh, and Kristen Grauman University of Texas at Austin yjlee0222@utexas.edu, joydeep@ece.utexas.edu,
More informationTop down saliency estimation via superpixel-based discriminative dictionaries
KOCAK ET AL.: TOP DOWN SALIENCY ESTIMATION 1 Top down saliency estimation via superpixel-based discriminative dictionaries Aysun Kocak aysunkocak@cs.hacettepe.edu.tr Kemal Cizmeciler kemalcizmeci@gmail.com
More informationDomain Generalization and Adaptation using Low Rank Exemplar Classifiers
Domain Generalization and Adaptation using Low Rank Exemplar Classifiers 报告人 : 李文 苏黎世联邦理工学院计算机视觉实验室 李文 苏黎世联邦理工学院 9/20/2017 1 Outline Problems Domain Adaptation and Domain Generalization Low Rank Exemplar
More informationTheta sequences are essential for internally generated hippocampal firing fields.
Theta sequences are essential for internally generated hippocampal firing fields. Yingxue Wang, Sandro Romani, Brian Lustig, Anthony Leonardo, Eva Pastalkova Supplementary Materials Supplementary Modeling
More informationAnnouncements. Perceptual Grouping. Quiz: Fourier Transform. What you should know for quiz. What you should know for quiz
Announcements Quiz on Tuesday, March 10. Material covered (Union not Intersection) All lectures before today (March 3). Forsyth and Ponce Readings: Chapters 1.1, 4, 5.1, 5.2, 5.3, 7,8, 9.1, 9.2, 9.3, 6.5.2,
More informationCONSTRAINED SEMI-SUPERVISED LEARNING ATTRIBUTES USING ATTRIBUTES AND COMPARATIVE
CONSTRAINED SEMI-SUPERVISED LEARNING USING ATTRIBUTES AND COMPARATIVE ATTRIBUTES Abhinav Shrivastava, Saurabh Singh, Abhinav Gupta The Robotics Institute Carnegie Mellon University SUPERVISION BIG-DATA
More informationNetwork Dissection: Quantifying Interpretability of Deep Visual Representation
Name: Pingchuan Ma Student number: 3526400 Date: August 19, 2018 Seminar: Explainable Machine Learning Lecturer: PD Dr. Ullrich Köthe SS 2018 Quantifying Interpretability of Deep Visual Representation
More informationImage processing mammography applications
Image processing mammography applications Isabelle Bloch Isabelle.Bloch@telecom-paristech.fr http://perso.telecom-paristech.fr/bloch LTCI, Télécom ParisTech Mammography p.1/27 Image processing for mammography
More informationarxiv: v1 [cs.cv] 21 Nov 2018
Rethinking ImageNet Pre-training Kaiming He Ross Girshick Piotr Dollár Facebook AI Research (FAIR) arxiv:1811.8883v1 [cs.cv] 21 Nov 218 Abstract We report competitive results on object detection and instance
More informationShu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with
More informationLearned Region Sparsity and Diversity Also Predict Visual Attention
Learned Region Sparsity and Diversity Also Predict Visual Attention Zijun Wei 1, Hossein Adeli 2, Gregory Zelinsky 1,2, Minh Hoai 1, Dimitris Samaras 1 1. Department of Computer Science 2. Department of
More informationMBios 478: Systems Biology and Bayesian Networks, 27 [Dr. Wyrick] Slide #1. Lecture 27: Systems Biology and Bayesian Networks
MBios 478: Systems Biology and Bayesian Networks, 27 [Dr. Wyrick] Slide #1 Lecture 27: Systems Biology and Bayesian Networks Systems Biology and Regulatory Networks o Definitions o Network motifs o Examples
More informationIdeal Observers for Detecting Motion: Correspondence Noise
Ideal Observers for Detecting Motion: Correspondence Noise HongJing Lu Department of Psychology, UCLA Los Angeles, CA 90095 HongJing@psych.ucla.edu Alan Yuille Department of Statistics, UCLA Los Angeles,
More informationDelving into Salient Object Subitizing and Detection
Delving into Salient Object Subitizing and Detection Shengfeng He 1 Jianbo Jiao 2 Xiaodan Zhang 2,3 Guoqiang Han 1 Rynson W.H. Lau 2 1 South China University of Technology, China 2 City University of Hong
More informationAnalyzing Appearance and Contour Based Methods for Object Categorization
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 03), Madison, USA, June 2003. Analyzing Apance and Contour Based Methods for Object Categorization Bastian Leibe and Bernt Schiele
More informationITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION
ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION Yunxiang Mao 1, Zhaozheng Yin 1, Joseph M. Schober 2 1 Missouri University of Science and Technology 2 Southern Illinois University
More informationM Cells. Why parallel pathways? P Cells. Where from the retina? Cortical visual processing. Announcements. Main visual pathway from retina to V1
Announcements exam 1 this Thursday! review session: Wednesday, 5:00-6:30pm, Meliora 203 Bryce s office hours: Wednesday, 3:30-5:30pm, Gleason https://www.youtube.com/watch?v=zdw7pvgz0um M Cells M cells
More informationMulti-attention Guided Activation Propagation in CNNs
Multi-attention Guided Activation Propagation in CNNs Xiangteng He and Yuxin Peng (B) Institute of Computer Science and Technology, Peking University, Beijing, China pengyuxin@pku.edu.cn Abstract. CNNs
More informationend-stage renal disease
Case study: AIDS and end-stage renal disease Robert Smith? Department of Mathematics and Faculty of Medicine The University of Ottawa AIDS and end-stage renal disease ODEs Curve fitting AIDS End-stage
More informationBayesian Nonparametric Methods for Precision Medicine
Bayesian Nonparametric Methods for Precision Medicine Brian Reich, NC State Collaborators: Qian Guan (NCSU), Eric Laber (NCSU) and Dipankar Bandyopadhyay (VCU) University of Illinois at Urbana-Champaign
More informationSupporting Information Identification of Amino Acids with Sensitive Nanoporous MoS 2 : Towards Machine Learning-Based Prediction
Supporting Information Identification of Amino Acids with Sensitive Nanoporous MoS 2 : Towards Machine Learning-Based Prediction Amir Barati Farimani, Mohammad Heiranian, Narayana R. Aluru 1 Department
More informationScientific Inquiry Review
Scientific Inquiry Review Adapted from Regentsprep.org Be able to USE AND APPLY the steps of the scientific method to solve a problem and design an experiment: Scientific Method: 1. Make observations about
More informationTumor cut segmentation for Blemish Cells Detection in Human Brain Based on Cellular Automata
Tumor cut segmentation for Blemish Cells Detection in Human Brain Based on Cellular Automata D.Mohanapriya 1 Department of Electronics and Communication Engineering, EBET Group of Institutions, Kangayam,
More informationComputational modeling of visual attention and saliency in the Smart Playroom
Computational modeling of visual attention and saliency in the Smart Playroom Andrew Jones Department of Computer Science, Brown University Abstract The two canonical modes of human visual attention bottomup
More informationAnalyzing Semantic Segmentation Using Hybrid Human-Machine CRFs
2013 IEEE Conference on Computer Vision and Pattern Recognition Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs Roozbeh Mottaghi UCLA roozbehm@cs.ucla.edu Sanja Fidler, Jian Yao, Raquel
More informationWhat is and What is not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors
What is and What is not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors Changqun Xia 1, Jia Li 1,2, Xiaowu Chen 1, Anlin Zheng 1, Yu Zhang 1 1 State Key Laboratory
More informationGESTALT SALIENCY: SALIENT REGION DETECTION BASED ON GESTALT PRINCIPLES
GESTALT SALIENCY: SALIENT REGION DETECTION BASED ON GESTALT PRINCIPLES Jie Wu and Liqing Zhang MOE-Microsoft Laboratory for Intelligent Computing and Intelligent Systems Dept. of CSE, Shanghai Jiao Tong
More informationAction Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem
Action Recognition Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem This section: advanced topics Convolutional neural networks in vision Action recognition Vision and Language 3D
More informationSemantic Image Retrieval via Active Grounding of Visual Situations
Semantic Image Retrieval via Active Grounding of Visual Situations Max H. Quinn 1, Erik Conser 1, Jordan M. Witte 1, and Melanie Mitchell 1,2 1 Portland State University 2 Santa Fe Institute Email: quinn.max@gmail.com
More informationLook, Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNs
Look, Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNs Xiaowu Chen 1, Anlin Zheng 1, Jia Li 1,2, Feng Lu 1,2 1 State Key Laboratory of Virtual Reality Technology
More informationStatistical Methods and Reasoning for the Clinical Sciences
Statistical Methods and Reasoning for the Clinical Sciences Evidence-Based Practice Eiki B. Satake, PhD Contents Preface Introduction to Evidence-Based Statistics: Philosophical Foundation and Preliminaries
More informationA Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges
REGULAR PAPER 1 A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges Dingwen Zhang, Huazhu Fu, Junwei Han, Senior Member, IEEE, Feng Wu, Fellow, IEEE arxiv:1604.07090v2
More informationBrain Tumor Detection using Watershed Algorithm
Brain Tumor Detection using Watershed Algorithm Dawood Dilber 1, Jasleen 2 P.G. Student, Department of Electronics and Communication Engineering, Amity University, Noida, U.P, India 1 P.G. Student, Department
More informationSaliency aggregation: Does unity make strength?
Saliency aggregation: Does unity make strength? Olivier Le Meur a and Zhi Liu a,b a IRISA, University of Rennes 1, FRANCE b School of Communication and Information Engineering, Shanghai University, CHINA
More informationWhat Is the Relationship Between the Amount of Transmitted Light Through a Solution and Its Concentration?
What Is the Relationship Between the Amount of Transmitted Light Through a Solution and Its Concentration? Blue Food Dye Treats Spine Injury in Rats HTTP://WWW.WIRED.COM/WIREDSCIENCE/2009/07/BLUERATS/
More informationVisual interpretation in pathology
13 Visual interpretation in pathology Tissue architecture (alteration) evaluation e.g., for grading prostate cancer Immunohistochemistry (IHC) staining scoring e.g., HER2 in breast cancer (companion diagnostic
More informationRecurrent Refinement for Visual Saliency Estimation in Surveillance Scenarios
2012 Ninth Conference on Computer and Robot Vision Recurrent Refinement for Visual Saliency Estimation in Surveillance Scenarios Neil D. B. Bruce*, Xun Shi*, and John K. Tsotsos Department of Computer
More informationGroup-Wise FMRI Activation Detection on Corresponding Cortical Landmarks
Group-Wise FMRI Activation Detection on Corresponding Cortical Landmarks Jinglei Lv 1,2, Dajiang Zhu 2, Xintao Hu 1, Xin Zhang 1,2, Tuo Zhang 1,2, Junwei Han 1, Lei Guo 1,2, and Tianming Liu 2 1 School
More informationConvolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN) Algorithm and Some Applications in Computer Vision Luo Hengliang Institute of Automation June 10, 2014 Luo Hengliang (Institute of Automation) Convolutional Neural Networks
More informationSupplementary Creativity: Generating Diverse Questions using Variational Autoencoders
Supplementary Creativity: Generating Diverse Questions using Variational Autoencoders Unnat Jain UIUC uj2@illinois.edu Ziyu Zhang Northwestern University zzhang@u.northwestern.edu Alexander Schwing UIUC
More informationNeuroMem. RBF Decision Space Mapping
NeuroMem RBF Decision Space Mapping Version 4.2 Revised 01/04/2017 This manual is copyrighted and published by General Vision Inc. All rights reserved. Contents 1 Introduction to a decision space... 3
More informationIJREAS Volume 2, Issue 2 (February 2012) ISSN: LUNG CANCER DETECTION USING DIGITAL IMAGE PROCESSING ABSTRACT
LUNG CANCER DETECTION USING DIGITAL IMAGE PROCESSING Anita Chaudhary* Sonit Sukhraj Singh* ABSTRACT In recent years the image processing mechanisms are used widely in several medical areas for improving
More informationThe Nottingham eprints service makes this work by researchers of the University of Nottingham available open access under the following conditions.
Bulat, Adrian and Tzimiropoulos, Georgios (2016) Human pose estimation via convolutional part heatmap regression. In: 14th European Conference on Computer Vision (EECV 2016), 8-16 October 2016, Amsterdam,
More informationPower-Based Connectivity. JL Sanguinetti
Power-Based Connectivity JL Sanguinetti Power-based connectivity Correlating time-frequency power between two electrodes across time or over trials Gives you flexibility for analysis: Test specific hypotheses
More informationProgressive Attention Guided Recurrent Network for Salient Object Detection
Progressive Attention Guided Recurrent Network for Salient Object Detection Xiaoning Zhang, Tiantian Wang, Jinqing Qi, Huchuan Lu, Gang Wang Dalian University of Technology, China Alibaba AILabs, China
More informationSupplementary material: Backtracking ScSPM Image Classifier for Weakly Supervised Top-down Saliency
Supplementary material: Backtracking ScSPM Image Classifier for Weakly Supervised Top-down Saliency Hisham Cholakkal Jubin Johnson Deepu Rajan Nanyang Technological University Singapore {hisham002, jubin001,
More informationConclusions and future directions
Chapter 9 Conclusions and future directions This chapter summarises the findings within this thesis, examines its main contributions, and provides suggestions for further directions. 9.1 Thesis summary
More informationChapter 3: Examining Relationships
Name Date Per Key Vocabulary: response variable explanatory variable independent variable dependent variable scatterplot positive association negative association linear correlation r-value regression
More informationMammogram Analysis: Tumor Classification
Mammogram Analysis: Tumor Classification Term Project Report Geethapriya Raghavan geeragh@mail.utexas.edu EE 381K - Multidimensional Digital Signal Processing Spring 2005 Abstract Breast cancer is the
More informationCHAPTER ONE CORRELATION
CHAPTER ONE CORRELATION 1.0 Introduction The first chapter focuses on the nature of statistical data of correlation. The aim of the series of exercises is to ensure the students are able to use SPSS to
More informationVision: Over Ov view Alan Yuille
Vision: Overview Alan Yuille Why is Vision Hard? Complexity and Ambiguity of Images. Range of Vision Tasks. More 10x10 images 256^100 = 6.7 x 10 ^240 than the total number of images seen by all humans
More informationLSTD: A Low-Shot Transfer Detector for Object Detection
LSTD: A Low-Shot Transfer Detector for Object Detection Hao Chen 1,2, Yali Wang 1, Guoyou Wang 2, Yu Qiao 1,3 1 Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China 2 Huazhong
More informationIntroduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018
Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this
More informationEfficient Boosted Exemplar-based Face Detection
Efficient Boosted Exemplar-based Face Detection Haoxiang Li, Zhe Lin, Jonathan Brandt, Xiaohui Shen, Gang Hua Stevens Institute of Technology Hoboken, NJ 07030 {hli18, ghua}@stevens.edu Adobe Research
More informationExemplar-Driven Top-Down Saliency Detection via Deep Association
Exemplar-Driven Top-Down Saliency Detection via Deep Association Shengfeng He 1, Rynson W.H. Lau 1, and Qingxiong Yang 2 1 Department of Computer Science, City University of Hong Kong 2 School of Information
More informationDetection and Classification of Lung Cancer Using Artificial Neural Network
Detection and Classification of Lung Cancer Using Artificial Neural Network Almas Pathan 1, Bairu.K.saptalkar 2 1,2 Department of Electronics and Communication Engineering, SDMCET, Dharwad, India 1 almaseng@yahoo.co.in,
More informationJoint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge
Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge Ryota Hinami 1,2, Tao Mei 3, and Shin ichi Satoh 2,1 1 The University of Tokyo, 2 National Institute of Infomatics,
More informationEARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE
EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE SAKTHI NEELA.P.K Department of M.E (Medical electronics) Sengunthar College of engineering Namakkal, Tamilnadu,
More informationSPICE: Semantic Propositional Image Caption Evaluation
SPICE: Semantic Propositional Image Caption Evaluation Presented to the COCO Consortium, Sept 2016 Peter Anderson1, Basura Fernando1, Mark Johnson2 and Stephen Gould1 1 Australian National University 2
More informationThe discriminant center-surround hypothesis for bottom-up saliency
Appears in the Neural Information Processing Systems (NIPS) Conference, 27. The discriminant center-surround hypothesis for bottom-up saliency Dashan Gao Vijay Mahadevan Nuno Vasconcelos Department of
More informationUNIT 1CP LAB 1 - Spaghetti Bridge
Name Date Pd UNIT 1CP LAB 1 - Spaghetti Bridge The basis of this physics class is the ability to design an experiment to determine the relationship between two quantities and to interpret and apply the
More informationImproving Saliency Models by Predicting Human Fixation Patches
Improving Saliency Models by Predicting Human Fixation Patches Rachit Dubey 1, Akshat Dave 2, and Bernard Ghanem 1 1 King Abdullah University of Science and Technology, Saudi Arabia 2 University of California
More informationCSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil
CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,
More information