Computer Vision Group UC Berkeley How should we combine high level and low level knowledge? Jitendra Malik UC Berkeley Recognition using regions is joint.

Slides:



Advertisements
Similar presentations
Shape Matching and Object Recognition using Low Distortion Correspondence Alexander C. Berg, Tamara L. Berg, Jitendra Malik U.C. Berkeley.
Advertisements

Classification using intersection kernel SVMs is efficient
Poselets: Body Part Detectors trained Using 3D Human Pose Annotations Lubomir Bourdev & Jitendra Malik ICCV 2009.
Presenter: Duan Tran (Part of slides are from Pedro’s)
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Classification using intersection kernel SVMs is efficient Joint work with Subhransu Maji and Alex Berg Jitendra Malik UC Berkeley.
- Recovering Human Body Configurations: Combining Segmentation and Recognition (CVPR’04) Greg Mori, Xiaofeng Ren, Alexei A. Efros and Jitendra Malik -
Large Scale Visual Recognition Challenge (ILSVRC) 2013: Detection spotlights.
Detecting Categories in News Video Using Image Features Slav Petrov, Arlo Faria, Pascal Michaillat, Alex Berg, Andreas Stolcke, Dan Klein, Jitendra Malik.
1 Building a Dictionary of Image Fragments Zicheng Liao Ali Farhadi Yang Wang Ian Endres David Forsyth Department of Computer Science, University of Illinois.
Global spatial layout: spatial pyramid matching Spatial weighting the features Beyond bags of features: Adding spatial information.
Boundary Preserving Dense Local Regions
1 P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. Contour Detection and Hierarchical image Segmentation. IEEE Trans. on PAMI, Student: Hsin-Min Cheng.
Enhancing Exemplar SVMs using Part Level Transfer Regularization 1.
Groups of Adjacent Contour Segments for Object Detection Vittorio Ferrari Loic Fevrier Frederic Jurie Cordelia Schmid.
Ghunhui Gu, Joseph J. Lim, Pablo Arbeláez, Jitendra Malik University of California at Berkeley Berkeley, CA
Contour Based Approaches for Visual Object Recognition Jamie Shotton University of Cambridge Joint work with Roberto Cipolla, Andrew Blake.
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection CVPR2013 POSTER.
Detecting Pedestrians by Learning Shapelet Features
Fast intersection kernel SVMs for Realtime Object Detection
Student: Yao-Sheng Wang Advisor: Prof. Sheng-Jyh Wang ARTICULATED HUMAN DETECTION 1 Department of Electronics Engineering National Chiao Tung University.
Computer Vision Group University of California Berkeley Shape Matching and Object Recognition using Shape Contexts Jitendra Malik U.C. Berkeley (joint.
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
1 Image Recognition - I. Global appearance patterns Slides by K. Grauman, B. Leibe.
Generic Object Detection using Feature Maps Oscar Danielsson Stefan Carlsson
CS335 Principles of Multimedia Systems Content Based Media Retrieval Hao Jiang Computer Science Department Boston College Dec. 4, 2007.
Region-based Voting Exemplar 1 Query 1 Exemplar 2.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
1 Learning to Detect Natural Image Boundaries David Martin, Charless Fowlkes, Jitendra Malik Computer Science Division University of California at Berkeley.
Berkeley Vision GroupNIPS Vancouver Learning to Detect Natural Image Boundaries Using Local Brightness,
Visual Grouping and Recognition David Martin UC Berkeley David Martin UC Berkeley.
Cliff Rhyne and Jerry Fu June 5, 2007 Parallel Image Segmenter CSE 262 Spring 2007 Project Final Presentation.
What, Where & How Many? Combining Object Detectors and CRFs
Global and Efficient Self-Similarity for Object Classification and Detection CVPR 2010 Thomas Deselaers and Vittorio Ferrari.
Generic object detection with deformable part-based models
The Three R’s of Vision Jitendra Malik.
1/24 Exploring the Design Space of a Parallel Object Recognition System Bor-Yiing Su, Kurt Keutzer,
1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.
“Secret” of Object Detection Zheng Wu (Summer intern in MSRNE) Sep. 3, 2010 Joint work with Ce Liu (MSRNE) William T. Freeman (MIT) Adam Kalai (MSRNE)
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Detecting Curved Symmetric Parts using a Deformable Disc Model Tom Sie Ho Lee, University of Toronto Sanja Fidler, TTI Chicago Sven Dickinson, University.
Detection, Segmentation and Fine-grained Localization
Lecture 29: Face Detection Revisited CS4670 / 5670: Computer Vision Noah Snavely.
Face detection Slides adapted Grauman & Liebe’s tutorial
Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao.
Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.
80 million tiny images: a large dataset for non-parametric object and scene recognition CS 4763 Multimedia Systems Spring 2008.
Pedestrian Detection and Localization
Deformable Part Models (DPM) Felzenswalb, Girshick, McAllester & Ramanan (2010) Slides drawn from a tutorial By R. Girshick AP 12% 27% 36% 45% 49% 2005.
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
Computer Vision Group University of California Berkeley On Visual Recognition Jitendra Malik UC Berkeley.
Geodesic Saliency Using Background Priors
Project 3 Results.
Object detection, deep learning, and R-CNNs
CS 1699: Intro to Computer Vision Detection II: Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 12, 2015.
Recognition Using Visual Phrases
Object Recognizing. Object Classes Individual Recognition.
Rich feature hierarchies for accurate object detection and semantic segmentation 2014 IEEE Conference on Computer Vision and Pattern Recognition Ross Girshick,
Fast Human Detection in Crowded Scenes by Contour Integration and Local Shape Estimation Csaba Beleznai, Horst Bischof Computer Vision and Pattern Recognition,
Jo˜ao Carreira, Abhishek Kar, Shubham Tulsiani and Jitendra Malik University of California, Berkeley CVPR2015 Virtual View Networks for Object Reconstruction.
Object detection with deformable part-based models
Recap: Advanced Feature Encoding
Object detection as supervised classification
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Rob Fergus Computer Vision
Brief Review of Recognition + Context
Outline Background Motivation Proposed Model Experimental Results
Liyuan Li, Jerry Kah Eng Hoe, Xinguo Yu, Li Dong, and Xinqi Chu
Presentation transcript:

Computer Vision Group UC Berkeley How should we combine high level and low level knowledge? Jitendra Malik UC Berkeley Recognition using regions is joint work with Chunhui Gu, Joseph Lim & Pablo Arbelaez (CVPR 2009)

Computer Vision Group UC Berkeley The central problems of vision Grouping / Segmentation 3D structure/ Figure-Ground Object and Scene Recognition

Computer Vision Group UC Berkeley Detection and Segmentation: Giraffes Orig. ImageSegmentation Orig. ImageSegmentation

Computer Vision Group UC Berkeley Detection and Segmentation: Mugs Orig. ImageSegmentation Orig. ImageSegmentation

Computer Vision Group UC Berkeley Outline Current paradigm: Multiscale scanning Our approach –Bottom up region segmentation –Hough transform style voting (learned weights) –Top down segmentation Results on ETHZ, Caltech 101, MSRC

Computer Vision Group UC Berkeley Detection: Is this an X? Ask this question repeatedly, varying position, scale, category… Paradigm introduced by Rowley, Baluja & Kanade 96 for face detection Viola & Jones 01, Dalal & Triggs 05, Felzenszwalb, McAllester, Ramanan 08

Computer Vision Group UC Berkeley Problems with the multi-scale scanning paradigm Computational complexity 10^6 windows, 10 scales, 10^4 categories Not natural for irregularly shaped objects Segmentation is delinked Context is delinked

Computer Vision Group UC Berkeley Our Approach Perceptual Organization provides the right primitives for visual recognition. After more than a decade of work, we finally have high quality, generic, detectors for contours and regions. We now only need to work with ~100 elements, each with its local scale estimate. In this talk, we demonstrate recognition using regions. Detection and segmentation happen in the same framework. There will always be some errors in the bottom-up grouping process, the recognition machinery needs to be robust to that.

Computer Vision Group UC Berkeley Contour Detection (CVPR 2008)

Computer Vision Group UC Berkeley Region Detection (CVPR 2009)

Computer Vision Group UC Berkeley Region detector wins on any measure! Region Benchmarks on BSDS Probabilistic Rand Index on BSDSVariation of Information on BSDS Region Benchmarks on MSRC/PASCAL08

Computer Vision Group UC Berkeley Parallelizing Image Segmentation Catanzaro et al, UC Berkeley, ICCV 09 GTX 280 is an Nvidia Graphics Processor, massively parallel general purpose computing platform –30 cores, 8 wide SIMD = 240 way parallelism –140 GB/s memory bandwidth (Modern CPUs have ~10-20 GB/s) –Special memory subsystems for graphics processing Sequential Implementation: 5 minutes per image Parallel, Optimized Implementation: 2 seconds

Computer Vision Group UC Berkeley Why Use Regions? Local estimate of scale; no search necessary Shape, color and texture in the same framework Hierarchy of regions (partonomy) represents scenes, objects, parts. Makes use of context natural. Do not suffer from background clutter Reduce candidate windows on detection task –1000 to times fewer windows on the ETHZ dataset Need to be robust to segmentation errors

Computer Vision Group UC Berkeley Object Representation using Regions Bag of Regions Region Segmentation

Computer Vision Group UC Berkeley Region Representation

Region-based Hough Voting Recover transformation from matched regions Transform exemplar bounding box to query 20 Exemplar Query T(x,y,s x,s y )

Region-based Voting Exemplar 1 Query 21

Region-based Voting Exemplar 1 Query 22

Region-based Voting Exemplar 1 Query 23

Region-based Voting Exemplar 1 Query 24