PSVMA+：探索用于广义零样本学习的多粒度语义-视觉自适应
PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning
AI总结：
针对广义零样本学习中属性与实例多样性导致的视觉-语义对应不足问题，提出多粒度渐进语义-视觉自适应网络PSVMA+，通过双语义-视觉变换器模块重塑属性并聚合视觉区域，结合选择性跨粒度学习融合多粒度特征，持续优于现有方法。
摘要：
广义零样本学习（GZSL）致力于利用可见领域的知识识别未见类别，这需要视觉特征与属性语义特征之间的内在交互。然而，由于属性多样性和实例多样性，GZSL面临视觉-语义对应不足的问题。属性多样性指属性描述中语义粒度的变化，从低级（具体、可直接观察）到高级（抽象、高度通用）特征。这种多样性挑战了在单一粒度下为属性收集充足视觉线索的能力。此外，对应相同共享属性的多样视觉实例引入了语义歧义，导致视觉模式模糊。为解决这些问题，我们提出了一种多粒度渐进语义-视觉相互自适应（PSVMA+）网络，能够跨粒度级别收集充足的视觉元素以弥补粒度不一致。PSVMA+在不同粒度级别探索语义-视觉交互，实现对视觉和语义元素中多粒度的感知。在每个粒度级别，双语义-视觉变换器模块（DSVTM）将共享属性重塑为以实例为中心的属性，并聚合语义相关的视觉区域，从而学习无歧义的视觉特征以适应各种实例。鉴于不同粒度的多样贡献，PSVMA+采用选择性跨粒度学习，利用来自可靠粒度的知识，并自适应融合多粒度特征以获得全面表示。实验结果表明，PSVMA+持续优于最先进的方法。
英文摘要：
Generalized zero-shot learning (GZSL) endeavors to identify the unseen categories using knowledge from the seen domain, necessitating the intrinsic interactions between the visual features and attribute semantic features. However, GZSL suffers from insufficient visual-semantic correspondences due to the attribute diversity and instance diversity. Attribute diversity refers to varying semantic granularity in attribute descriptions, ranging from low-level (specific, directly observable) to high-level (abstract, highly generic) characteristics. This diversity challenges the collection of adequate visual cues for attributes under a uni-granularity. Additionally, diverse visual instances corresponding to the same sharing attributes introduce semantic ambiguity, leading to vague visual patterns. To tackle these problems, we propose a multi-granularity progressive semantic-visual mutual adaption (PSVMA+) network, where sufficient visual elements across granularity levels can be gathered to remedy the granularity inconsistency. PSVMA+ explores semantic-visual interactions at different granularity levels, enabling awareness of multi-granularity in both visual and semantic elements. At each granularity level, the dual semantic-visual transformer module (DSVTM) recasts the sharing attributes into instance-centric attributes and aggregates the semantic-related visual regions, thereby learning unambiguous visual features to accommodate various instances. Given the diverse contributions of different granularities, PSVMA+ employs selective cross-granularity learning to leverage knowledge from reliable granularities and adaptively fuses multi-granularity features for comprehensive representations. Experimental results demonstrate that PSVMA+ consistently outperforms state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
