Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 42, Issue 12, Pages 3136-3152Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2922175
Keywords
Semantics; Vocabulary; Training data; Prototypes; Image recognition; Visualization; Learning systems; Vocabulary-informed learning; generalized zero-shot learning; open-set recognition; zero-shot learning
Funding
- NSFC [61702108, 61622204]
- STCSM Project [16JC1420400]
- Shanghai Municipal Science and Technology Major Project [2017SHZDZX01, 2018SHZDZX01]
- ZJLab
- Eastern Scholar [TP2017006]
Ask authors/readers for more resources
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available