Conference proceeding
Learning Attributes Equals Multi-Source Domain Generalization
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol.2016-, pp.87-97
06/2016
DOI: 10.1109/CVPR.2016.17
Abstract
Attributes possess appealing properties and benefit many computer vision problems, such as object recognition, learning with humans in the loop, and image retrieval. Whereas the existing work mainly pursues utilizing attributes for various computer vision problems, we contend that the most basic problem-how to accurately and robustly detect attributes from images-has been left under explored. Especially, the existing work rarely explicitly tackles the need that attribute detectors should generalize well across different categories, including those previously unseen. Noting that this is analogous to the objective of multi-source domain generalization, if we treat each category as a domain, we provide a novel perspective to attribute detection and propose to gear the techniques in multi-source domain generalization for the purpose of learning cross-category generalizable attribute detectors. We validate our understanding and approach with extensive experiments on four challenging datasets and three different problems.
Details
- Title: Subtitle
- Learning Attributes Equals Multi-Source Domain Generalization
- Creators
- Chuang Gan - Tsinghua UniversityTianbao Yang - University of IowaBoqing Gong - CRCV, U. of Central Florida, Orlando, FL, USA
- Resource Type
- Conference proceeding
- Publication Details
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol.2016-, pp.87-97
- DOI
- 10.1109/CVPR.2016.17
- ISSN
- 1063-6919
- eISSN
- 1063-6919
- Publisher
- IEEE
- Language
- English
- Date published
- 06/2016
- Academic Unit
- Computer Science
- Record Identifier
- 9984259467902771
Metrics
26 Record Views