We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Semantics-Guided Intra-Category Knowledge Transfer for Generalized Zero-Shot Learning.
- Authors
Yang, Fu-En; Lee, Yuan-Hao; Lin, Chia-Ching; Wang, Yu-Chiang Frank
- Abstract
Zero-shot learning (ZSL) requires one to associate visual and semantic information observed from data of seen classes, so that test data of unseen classes can be recognized based on the described semantic representation. Aiming at synthesizing visual data from the given semantic inputs, hallucination-based ZSL approaches might suffer from mode collapse and biased problems due to the lack of ability in modeling the desirable visual features for unseen categories. In this paper, we present a generative model of Cross-Modal Consistency GAN (CMC-GAN), which performs semantics-guided intra-category knowledge transfer across image categories, so that data hallucination for unseen classes can be achieved with proper semantics and sufficient visual diversity. In our experiments, we perform standard and generalized ZSL on four benchmark datasets, confirming the effectiveness of our approach over that of state-of-the-art ZSL methods.
- Subjects
KNOWLEDGE transfer; PROBABILISTIC generative models; COMPUTER vision; DEEP learning; GENERATIVE adversarial networks
- Publication
International Journal of Computer Vision, 2023, Vol 131, Issue 6, p1331
- ISSN
0920-5691
- Publication type
Article
- DOI
10.1007/s11263-023-01767-0