通过扩散映射的测地原型匹配用于可解释的细粒度识别
Geodesic Prototype Matching via Diffusion Maps for Interpretable Fine-Grained Recognition
AI总结：
本文提出通过扩散映射的测地原型匹配方法，用于可解释的细粒度识别，通过内在几何结构提升原型的语义对应性。
摘要：
非线性流形在深度视觉特征中普遍存在，其中欧几里得距离可能无法准确表示真实相似性。这种不匹配对基于原型的可解释细粒度识别尤其有害，因为即使细微的语义差异也至关重要。为缓解这一问题，本文提出了一种新的基于原型的识别范式，通过将相似性 grounding 在深度特征的内在几何结构中。具体来说，我们将每个类别的潜在流形结构蒸馏到扩散空间中，并且关键地设计了可微的Nyström插值，使这种几何结构对未见过的样本和可学习的原型可访问。为了保持效率，我们采用紧凑的每类地标集并进行周期性更新。这种策略使嵌入保持与演进的backbone同步，从而在大规模情况下实现快速推理。在两个基准数据集上的全面实验表明，我们的GeoProto生成的原型聚焦于语义对应的部分，显著优于欧几里得原型网络。
英文摘要：
Nonlinear manifolds are pervasive in deep visual features, where Euclidean distances can misrepresent true similarity. This mismatch is particularly detrimental to prototype-based interpretable fine-grained recognition, where even subtle semantic distinctions are crucial. To mitigate this issue, this work presents a novel paradigm for prototype-based recognition by grounding similarity in the intrinsic geometry of deep features. Concretely, we distill the latent manifold structure of each class into a diffusion space and, critically, devise a differentiable Nyström interpolation to make this geometry accessible to both unseen samples and learnable prototypes. To maintain efficiency, we employ compact per-class landmark sets with periodic updates. This strategy keeps the embedding synchronized with the evolving backbone, enabling fast inference at scale. Comprehensive experiments on two benchmark datasets demonstrate that our GeoProto yields prototypes focusing on semantically corresponding parts, significantly outperforming Euclidean prototype networks.
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。
