Scholarlink

<p>Generative zero-shot learning (ZSL) recognizes novel categories by employing a cross-modal generative model conditioned on semantic factors (such as attributes) to transfer knowledge from seen classes to unseen ones. Many existing generative ZSL methods rely solely on feature extraction models pre-trained on ImageNet, disregarding the cross-dataset bias between ImageNet and ZSL benchmarks. This bias inevitably leads to suboptimal visual features that lack semantic relevance to the predefined attributes, constraining the generator’s ability to synthesize semantically meaningful visual features for generative ZSL. In this paper, we introduce a visual feature refinement method (ViFR) to mitigate cross-dataset bias and advance generative ZSL. Given a generative ZSL model, ViFR incorporates both pre-feature refinement (Pre-FR) and post-feature refinement (Post-FR) modules to simultaneously enhance visual features. In Pre-FR, ViFR aims to learn attribute localization for discriminative visual feature representations using an attribute-guided attention mechanism optimized with attribute-based cross-entropy loss. In Post-FR, ViFR learns an effective visual<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11263_2025_2394_Article_IEq1.gif" Format="GIF" Height="6" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">\(\rightarrow \)</EquationSource> <EquationSource Format="MATHML"><math> <mo stretchy="false">→</mo> </math></EquationSource> </InlineEquation>semantic mapping by integrating the semantic-conditioned generator into a unified generative model to enhance visual features. Additionally, we propose a self-adaptive margin center loss (SAMC-loss) that collaborates with semantic cycle-consistency loss to guide Post-FR in learning class- and semantically-relevant representations. The features in Post-FR are concatenated to form fully refined visual features for ZSL classification. Extensive experiments on benchmark datasets (i.e., CUB, SUN, and AWA2) demonstrate that ViFR outperforms state-of-the-art ZSL approaches. Our implementation is publicly available at <a href="https://github.com/shiming-chen/ViFR">https://github.com/shiming-chen/ViFR</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Semantics-Conditioned Generative Zero-Shot Learning via Feature Refinement

  • 期刊论文

  • 发表日期：

    2025年3月10日

查看全文
  • Shiming Chen,
  • Ziming Hong,
  • Xinge You,
  • Ling Shao

摘要

Generative zero-shot learning (ZSL) recognizes novel categories by employing a cross-modal generative model conditioned on semantic factors (such as attributes) to transfer knowledge from seen classes to unseen ones. Many existing generative ZSL methods rely solely on feature extraction models pre-trained on ImageNet, disregarding the cross-dataset bias between ImageNet and ZSL benchmarks. This bias inevitably leads to suboptimal visual features that lack semantic relevance to the predefined attributes, constraining the generator’s ability to synthesize semantically meaningful visual features for generative ZSL. In this paper, we introduce a visual feature refinement method (ViFR) to mitigate cross-dataset bias and advance generative ZSL. Given a generative ZSL model, ViFR incorporates both pre-feature refinement (Pre-FR) and post-feature refinement (Post-FR) modules to simultaneously enhance visual features. In Pre-FR, ViFR aims to learn attribute localization for discriminative visual feature representations using an attribute-guided attention mechanism optimized with attribute-based cross-entropy loss. In Post-FR, ViFR learns an effective visual \(\rightarrow \) → semantic mapping by integrating the semantic-conditioned generator into a unified generative model to enhance visual features. Additionally, we propose a self-adaptive margin center loss (SAMC-loss) that collaborates with semantic cycle-consistency loss to guide Post-FR in learning class- and semantically-relevant representations. The features in Post-FR are concatenated to form fully refined visual features for ZSL classification. Extensive experiments on benchmark datasets (i.e., CUB, SUN, and AWA2) demonstrate that ViFR outperforms state-of-the-art ZSL approaches. Our implementation is publicly available at https://github.com/shiming-chen/ViFR.