NDLI: Structured Learning of Sum-of-Submodular Higher Order Energy Functions

Content Provider	IEEE Xplore Digital Library
Author	Fix, A. Joachims, T. Sung Min Park Zabih, R.
Copyright Year	2013
Description	Author affiliation: Comput. Sci. Dept., Cornell Univ., Ithaca, NY, USA (Fix, A.; Joachims, T.; Sung Min Park; Zabih, R.)
Abstract	Sub modular functions can be exactly minimized in polynomial time, and the special case that graph cuts solve with max flow [19] has had significant impact in computer vision [5, 21, 28]. In this paper we address the important class of sum-of-sub modular (SoS) functions [2, 18], which can be efficiently minimized via a variant of max flow called sub modular flow [6]. SoS functions can naturally express higher order priors involving, e.g., local image patches, however, it is difficult to fully exploit their expressive power because they have so many parameters. Rather than trying to formulate existing higher order priors as an SoS function, we take a discriminative learning approach, effectively searching the space of SoS functions for a higher order prior that performs well on our training set. We adopt a structural SVM approach [15, 34] and formulate the training problem in terms of quadratic programming, as a result we can efficiently search the space of SoS priors via an extended cutting-plane algorithm. We also show how the state-of-the-art max flow method for vision problems [11] can be modified to efficiently solve the sub modular flow problem. Experimental comparisons are made against the OpenCV implementation of the Grab Cut interactive segmentation technique [28], which uses hand-tuned parameters instead of machine learning. On a standard dataset [12] our method learns higher order priors with hundreds of parameter values, and produces significantly better segmentations. While our focus is on binary labeling problems, we show that our techniques can be naturally generalized to handle more than two labels.
Sponsorship	IEEE Comput. Soc.
Starting Page	3104
Ending Page	3111
File Size	2421065
Page Count	8
File Format	PDF
ISBN	9781479928408
ISSN	15505499
DOI	10.1109/ICCV.2013.385
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-12-01
Publisher Place	Australia
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Vectors Support vector machines Minimization Optimization Computer vision Computational modeling Structured prediction Max flow Graph cuts
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Order-Preserving Moves for Graph-Cut-Based Optimization

Reconfigurable models for scene recognition

Image classification using HTM cortical learning algorithms

Efficient Large-Scale Structured Learning

Learning Graph Matching

Minimizing Nonsubmodular Functions with Graph Cuts-A Review

Multi-stage Contextual Deep Learning for Pedestrian Detection

A Linear Max K-min classifier

A Convex Optimization Framework for Active Learning

Structured Learning of Sum-of-Submodular Higher Order Energy Functions

Similar Documents

Order-Preserving Moves for Graph-Cut-Based Optimization

Reconfigurable models for scene recognition

Image classification using HTM cortical learning algorithms

Efficient Large-Scale Structured Learning

Learning Graph Matching

Minimizing Nonsubmodular Functions with Graph Cuts-A Review

Multi-stage Contextual Deep Learning for Pedestrian Detection

A Linear Max K-min classifier

A Convex Optimization Framework for Active Learning

Structured Learning of Sum-of-Submodular Higher Order Energy Functions