NDLI: Learning to segment under various forms of weak supervision

Content Provider	IEEE Xplore Digital Library
Author	Jia Xu Schwing, A.G. Urtasun, R.
Copyright Year	2015
Description	Author affiliation: Univ. of Wisconsin - Madison, Madison, WI, USA (Jia Xu) \|\| Univ. of Toronto, Toronto, ON, Canada (Schwing, A.G.; Urtasun, R.)
Abstract	Despite the promising performance of conventional fully supervised algorithms, semantic segmentation has remained an important, yet challenging task. Due to the limited availability of complete annotations, it is of great interest to design solutions for semantic segmentation that take into account weakly labeled data, which is readily available at a much larger scale. Contrasting the common theme to develop a different algorithm for each type of weak annotation, in this work, we propose a unified approach that incorporates various forms of weak supervision - image level tags, bounding boxes, and partial labels - to produce a pixel-wise labeling. We conduct a rigorous evaluation on the challenging Siftflow dataset for various weakly labeled settings, and show that our approach outperforms the state-of-the-art by 12% on per-class accuracy, while maintaining comparable per-pixel accuracy.
Starting Page	3781
Ending Page	3790
File Size	458955
Page Count	10
File Format	PDF
ISSN	10636919
e-ISBN	9781467369640
DOI	10.1109/CVPR.2015.7299002
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-06-07
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Semantics Image segmentation Training Optimization Labeling Support vector machines Linear programming
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

Weakly-Supervised Dual Clustering for Image Semantic Segmentation

Region-based Image Annotation using Asymmetrical Support Vector Machine-based Multiple-Instance Learning

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

A Convex Optimization Framework for Active Learning

Large-Scale Video Summarization Using Web-Image Priors

Foreground segmentation of live videos using locally competing 1SVMs

Label Propagation from ImageNet to 3D Point Clouds

A Linear Max K-min classifier

Learning of Multilabel Classifiers

Learning to segment under various forms of weak supervision

Similar Documents

Weakly-Supervised Dual Clustering for Image Semantic Segmentation

Region-based Image Annotation using Asymmetrical Support Vector Machine-based Multiple-Instance Learning

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

A Convex Optimization Framework for Active Learning

Large-Scale Video Summarization Using Web-Image Priors

Foreground segmentation of live videos using locally competing 1SVMs

Label Propagation from ImageNet to 3D Point Clouds

A Linear Max K-min classifier

Learning of Multilabel Classifiers

Learning to segment under various forms of weak supervision