Exploiting Semantic Attributes for Transductive Zero-Shot Learning

arXiv (Cornell University)(2023)

引用 0|浏览1
暂无评分
摘要
Zero-shot learning (ZSL) aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. A recent paradigm called transductive zero-shot learning further leverages unlabeled unseen data during training and has obtained impressive results. These methods always synthesize unseen features from attributes through a generative adversarial network to mitigate the bias towards seen classes. However, they neglect the semantic information in the unlabeled unseen data and thus fail to generate high-fidelity attribute-consistent unseen features. To address this issue, we present a novel transductive ZSL method that produces semantic attributes of the unseen data and imposes them on the generative process. In particular, we first train an attribute decoder that learns the mapping from visual features to semantic attributes. Then, from the attribute decoder, we obtain pseudo-attributes of unlabeled data and integrate them into the generative model, which helps capture the detailed differences within unseen classes so as to synthesize more discriminative features. Experiments on five standard benchmarks show that our method yields state-of-the-art results for zero-shot learning.
更多
查看译文
关键词
semantic attributes,learning,zero-shot
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要