Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning

arXiv:2404.14808v1 Announce Type: new
Abstract: Generative Zero-shot learning (ZSL) learns a generator to synthesize visual samples for unseen classes, which is an effective way to advance ZSL. However, existing generative methods rely on the conditions of Gaussian noise and the predefined semantic prototype, which limit the generator only optimized on specific seen classes rather than characterizing each visual instance, resulting in poor generalizations (\textit{e.g.}, overfitting to seen classes). To address this issue, we propose a novel Visual-Augmented Dynamic Semantic prototype …

abstract advance arxiv cs.cv dynamic generative generator however noise samples semantic type visual zero-shot