这看起来明显像那：在Stiefel几何中基于可解释识别对抗神经崩溃
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse
AI总结：
本文提出AMP框架，利用Stiefel几何上的Riemannian优化提升原型网络的可解释性，通过正交基和空间正则化器减少原型崩溃问题，实现更准确的分类和更高的因果可信度。
摘要：
原型网络提供了一种内在的基于案例的解释机制，但其可解释性常常受到原型崩溃的阻碍，其中多个原型退化为高度冗余的证据。我们将这种失败模式归因于神经崩溃的终端动态，其中交叉熵优化抑制了类内方差并驱动类条件特征趋向于低维极限。为缓解这一问题，我们提出了自适应流形原型（AMP），该框架利用Riemannian优化在Stiefel流形上表示类原型作为正交基，并通过构造使秩一原型崩溃不可行。AMP进一步通过在非负容量向量上进行近端梯度更新学习类特定的有效秩，并引入空间正则化器以减少旋转模糊性并鼓励局部、非重叠的部分证据。在细粒度基准上的广泛实验表明，AMP在显著提高因果可信度的同时实现了最先进的分类精度。
英文摘要：
Prototype networks provide an intrinsic case based explanation mechanism, but their interpretability is often undermined by prototype collapse, where multiple prototypes degenerate to highly redundant evidence. We attribute this failure mode to the terminal dynamics of Neural Collapse, where cross entropy optimization suppresses intra class variance and drives class conditional features toward a low dimensional limit. To mitigate this, we propose Adaptive Manifold Prototypes (AMP), a framework that leverages Riemannian optimization on the Stiefel manifold to represent class prototypes as orthonormal bases and make rank one prototype collapse infeasible by construction. AMP further learns class specific effective rank via a proximal gradient update on a nonnegative capacity vector, and introduces spatial regularizers that reduce rotational ambiguity and encourage localized, non overlapping part evidence. Extensive experiments on fine-grained benchmarks demonstrate that AMP achieves state-of-the-art classification accuracy while significantly improving causal faithfulness over prior interpretable models.
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。
