Hanze Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hanze Dong has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Leonid Sigal
University of British Columbia
1 shared publication - Meng Wang
Hefei University of Technology, Hefei, China
1 shared publication - Xiangyang Xue
Fudan University, Shanghai, China
1 shared publication - Xiaomei Wang
Fudan University
1 shared publication - Yanwei Fu
Fudan University, Shanghai, China
1 shared publication - Yu-Gang Jiang
Fudan University, China
1 shared publication
Latest Publications
- 11 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 42 (12) , 3136-3152
Vocabulary-Informed Zero-Shot and Open-Set Learning
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, ability to learn from limited labeled data and ability 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 AwA and ImageNet datasets.
- 11 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 42 (12) , 3136-3152
Vocabulary-Informed Zero-Shot and Open-Set Learning
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, ability to learn from limited labeled data and ability 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 AwA and ImageNet datasets.