We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Unbiased hybrid generation network for zero-shot learning.
- Authors
Wang, Zong-Hui; Lu, Zi-Qian; Lu, Zhe-Ming
- Abstract
While promising progress has been achieved in the zero-shot learning (ZSL) task. The existing approaches still suffer from the strong bias problem between the unseen and seen classes. This Letter presents a unified feature generating framework equipped with a boundary decision loss to tackle this issue in ZSL. Specifically, the hybrid semantic and visual classification strategy is proposed, which can effectively align the bidirectional visual-semantic interactions. Furthermore, this Letter introduces a decision loss that optimises the decision boundary of seen and unseen classes to further alleviate the confusion of generated features. Extensive experiments on three popular datasets animals with attributes, Caltech-UCSD-Birds 200-2011, and SUN show that the proposed approach outperforms previous state-of-the-art works under both traditional ZSL and challenging generalised ZSL settings.
- Subjects
GENERATIONS; LEARNING
- Publication
Electronics Letters (Wiley-Blackwell), 2020, Vol 56, Issue 18, p929
- ISSN
0013-5194
- Publication type
Article
- DOI
10.1049/el.2020.1594