paper-with-me

Papers

Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification

2026-06-25 · Duarte Leão, Diogo Pereira Araújo, Catarina Barata, Carlos Santiago arxiv

Prototype-based neural networks aim to provide intrinsic interpretability by grounding predictions in a small set of part prototypes. However, modern vision backbones typically operate in normalized, directional embedding spaces where each semantic part exhibits substantial intra-class variability. As a result, point prototypes often become redundant or unstable, hurting both explanation quality and robustness. We propose vMFProto, a distributional part-prototype framework that models each class as a mixture of von Mises-Fisher components on the hypersphere. Each prototype learns its own concentration, capturing part-specific variability, and we use entropic optimal transport (OT) to obtain structured patch-to-prototype assignments. A two-stage training schedule performs OT-driven prototype discovery followed by end-to-end refinement with patch-level distillation and distribution-aware diversity regularization. Experiments on CUB-200-2011, Stanford Dogs, and Stanford Cars with frozen DINO backbones show that vMFProto achieves state-of-the-art explanation quality (consistency, stability, and distinctiveness) with competitive accuracy. Qualitative results confirm that vMFProto yields localized, non-redundant part evidence.

📄 PDF Abstract BibTeX arXiv:2606.27582

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling

2025-02-15 · Xu Shen, Yixin Liu, Yili Wang, Rui Miao 외

Out-of-distribution (OOD) generalization has emerged as a critical challenge in graph learning, as real-world graph data often exhibit diverse and shifting environments that traditional models fail to generalize across. …

Graph Learning

Hyperspherical Prototype Networks

2019-01-29 · NeurIPS 2019 12 · Pascal Mettes, Elise van der Pol, Cees G. M. Snoek

This paper introduces hyperspherical prototype networks, which unify classification and regression with prototypes on hyperspherical output spaces. For classification, a common approach is to define prototypes as the mea…

ClassificationGeneral Classificationregression

Distributional Clustering: A distribution-preserving clustering method

2019-11-14 · Arvind Krishna, Simon Mak, Roshan Joseph

One key use of k-means clustering is to identify cluster prototypes which can serve as representative points for a dataset. However, a drawback of using k-means cluster centers as representative points is that such point…

Clustering

HYPO: Hyperspherical Out-of-Distribution Generalization

2024-02-12 · Haoyue Bai, Yifei Ming, Julian Katz-Samuels, Yixuan Li

Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world. However, achieving this can be fundamentally challenging, as it requires the ability to learn invariant feature…

Out-of-Distribution Generalization

Hyperbolic Busemann Learning with Ideal Prototypes

2021-06-28 · NeurIPS 2021 12 · Mina Ghadimi Atigh, Martin Keller-Ressel, Pascal Mettes

Hyperbolic space has become a popular choice of manifold for representation learning of various datatypes from tree-like structures and text to graphs. Building on the success of deep learning with prototypes in Euclidea…

PositionRepresentation Learning