H3Former：基于超图的语义感知聚合，通过双曲层次对比损失进行细粒度视觉分类
H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification
AI总结：
针对细粒度视觉分类难题，提出H3Former框架，通过语义感知聚合模块利用多尺度上下文线索构建加权超图捕捉高阶语义依赖，引入双曲层次对比损失增强语义约束，实验验证了该框架在FGVC任务中的优越性。
摘要：
细粒度视觉分类（FGVC）因类间差异细微和类内变化大而仍具挑战性。现有方法常依赖特征选择机制或区域提议策略来定位用于语义分析的判别区域，但这些方法在引入大量类别无关冗余的同时，往往无法全面捕捉判别线索。为解决这些局限，我们提出H3Former，这是一个新颖的从令牌到区域的框架，利用高阶语义关系通过结构化区域级建模聚合局部细粒度表示。具体而言，我们提出语义感知聚合模块（SAAM），它利用多尺度上下文线索在令牌间动态构建加权超图。通过应用超图卷积，SAAM捕捉高阶语义依赖并逐步将令牌特征聚合为紧凑的区域级表示。此外，我们引入双曲层次对比损失（HHCL），在非欧几里得嵌入空间中强制进行层次语义约束。HHCL增强类间可分离性和类内一致性，同时保留细粒度类别间的内在层次关系。在四个标准FGVC基准上进行的综合实验验证了我们的H3Former框架的优越性。
英文摘要：
Fine-Grained Visual Classification (FGVC) remains a challenging task due to subtle inter-class differences and large intra-class variations. Existing approaches typically rely on feature-selection mechanisms or region-proposal strategies to localize discriminative regions for semantic analysis. However, these methods often fail to capture discriminative cues comprehensively while introducing substantial category-agnostic redundancy. To address these limitations, we propose H3Former, a novel token-to-region framework that leverages high-order semantic relations to aggregate local fine-grained representations with structured region-level modeling. Specifically, we propose the Semantic-Aware Aggregation Module (SAAM), which exploits multi-scale contextual cues to dynamically construct a weighted hypergraph among tokens. By applying hypergraph convolution, SAAM captures high-order semantic dependencies and progressively aggregates token features into compact region-level representations. Furthermore, we introduce the Hyperbolic Hierarchical Contrastive Loss (HHCL), which enforces hierarchical semantic constraints in a non-Euclidean embedding space. The HHCL enhances inter-class separability and intra-class consistency while preserving the intrinsic hierarchical relationships among fine-grained categories. Comprehensive experiments conducted on four standard FGVC benchmarks validate the superiority of our H3Former framework.
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。
