期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 42, 期 12, 页码 3136-3152出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2922175
关键词
Semantics; Vocabulary; Training data; Prototypes; Image recognition; Visualization; Learning systems; Vocabulary-informed learning; generalized zero-shot learning; open-set recognition; zero-shot learning
资金
- NSFC [61702108, 61622204]
- STCSM Project [16JC1420400]
- Shanghai Municipal Science and Technology Major Project [2017SHZDZX01, 2018SHZDZX01]
- ZJLab
- Eastern Scholar [TP2017006]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据