MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence

Author(s)
Rubinstein, Michael; Liu, Ce; Freeman, William T.
Thumbnail
Download11263_2016_Article_894.pdf (8.335Mb)
PUBLISHER_CC

Publisher with Creative Commons License

Creative Commons Attribution

Terms of use
Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/
Metadata
Show full item record
Abstract
We present a principled framework for inferring pixel labels in weakly-annotated image datasets. Most previous, example-based approaches to computer vision rely on a large corpus of densely labeled images. However, for large, modern image datasets, such labels are expensive to obtain and are often unavailable. We establish a large-scale graphical model spanning all labeled and unlabeled images, then solve it to infer pixel labels jointly for all images in the dataset while enforcing consistent annotations over similar visual patterns. This model requires significantly less labeled data and assists in resolving ambiguities by propagating inferred annotations from images with stronger local visual evidences to images with weaker local evidences. We apply our proposed framework to two computer vision problems, namely image annotation with semantic segmentation, and object discovery and co-segmentation (segmenting multiple images containing a common object). Extensive numerical evaluations and comparisons show that our method consistently outperforms the state-of-the-art in automatic annotation and semantic labeling, while requiring significantly less labeled data. In contrast to previous co-segmentation techniques, our method manages to discover and segment objects well even in the presence of substantial amounts of noise images (images not containing the common object), as typical for datasets collected from Internet search.
Date issued
2016-03
URI
http://hdl.handle.net/1721.1/106941
Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Journal
International Journal of Computer Vision
Publisher
Springer US
Citation
Rubinstein, Michael, Ce Liu, and William T. Freeman. “Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence.” International Journal of Computer Vision 119.1 (2016): 23–45.
Version: Final published version
ISSN
0920-5691
1573-1405

Collections
  • MIT Open Access Articles

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.