Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification

• URL: http://arxiv.org/abs/2606.27582v2
• Date: Tue, 30 Jun 2026 13:35:47 GMT
• Title: Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification
• Abstract summary: Prototype-based neural networks aim to provide intrinsic interpretability by grounding predictions in a small set of part prototypes.<n>Modern vision backbones typically operate in normalized, directional embedding spaces where each semantic part exhibits substantial intra-class variability.<n>We propose vMFProto, a distributional part-prototype framework that models each class as a mixture of von Mises-Fisher components on the hypersphere.
• Score: 9.050510996987436
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Traits Run Deeper: Trait-Specific Asymmetric Fusion for Personality Assessment [53.50824432699408]
  Traits Run Deeper is a novel personality assessment framework.<n>It consists of three components: the Multimodal Foundation Representation (MFR), the Trait-Specific Modality Fusion (TSMF) and the Distribution-Calibrated Personality Regression (DCPR)
  arXiv  Detail & Related papers  (2026-06-09T06:38:36Z)
• Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classification [28.25868366778138]
  DFPL is a novel framework for fine-grained prototype learning.<n>SSPM extracts compact and diverse shared and modality-specific prototypes.<n>PFA module jointly enforces prototype-level distribution matching and prototype-to-class semantic alignment.
  arXiv  Detail & Related papers  (2026-06-03T21:24:05Z)
• ProtoTTA: Prototype-Guided Test-Time Adaptation [8.178991486617972]
  We introduce ProtoTTA, a framework for prototypical models that leverage intermediate prototype signals rather than relying solely on model outputs.<n>ProtoTTA minimizes the entropy of the prototype-similarity distribution to encourage more confident and prototype-specific activations on shifted data.<n>We also introduce novel interpretability metrics and a vision-language minimization model (VLM) evaluation framework to explain TTA dynamics.
  arXiv  Detail & Related papers  (2026-04-16T19:52:57Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Image Segmentation [66.82598255715696]
  Federated learning enables multiple medical institutions to train a global model without sharing data.<n>Current approaches primarily focus on final-layer features, overlooking critical multi-level cues.<n>We propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment.
  arXiv  Detail & Related papers  (2025-11-14T04:15:34Z)
• DPL: Spatial-Conditioned Diffusion Prototype Enhancement for One-Shot Medical Segmentation [0.0]
  One-shot medical image segmentation faces fundamental challenges in prototype representation due to limited annotated data and anatomical variability across patients.<n>Traditional prototype-based methods rely on deterministic averaging of support features, creating brittle representations that fail to capture intra-class diversity essential for robust generalization.<n>This work introduces Diffusion Prototype Learning, a novel framework that reformulates prototype construction through diffusion-based feature space exploration.
  arXiv  Detail & Related papers  (2025-10-14T05:28:58Z)
• Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation [12.971351926107289]
  Prototype Expansion Network (PENet) is a framework that constructs big-capacity prototypes from two annotated feature sources.<n>PENet significantly outperforms state-of-the-art methods across various few-shot settings.
  arXiv  Detail & Related papers  (2025-09-16T09:29:46Z)
• Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation [75.18058114915327]
  Generalized Few-Shot Semanticnative (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples.<n>We propose FewCLIP, a probabilistic prototype calibration framework over multi-modal prototypes from the pretrained CLIP.<n>We show FewCLIP significantly outperforms state-of-the-art approaches across both GFSS and class-incremental setting.
  arXiv  Detail & Related papers  (2025-06-28T18:36:22Z)
• Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition [15.685927265270085]
  We present a new generative paradigm to learn prototype distributions, termed as Mixture of Gaussian-distributed Prototypes (MGProto)<n>MGProto achieves state-of-the-art image recognition and OoD detection performances, while providing encouraging interpretability results.
  arXiv  Detail & Related papers  (2023-11-30T11:01:37Z)
• Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation [55.339405417090084]
  We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
  arXiv  Detail & Related papers  (2021-11-09T08:14:50Z)
• Universal-Prototype Augmentation for Few-Shot Object Detection [128.4592084104352]
  Few-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. To alleviate the constraint of few samples, enhancing the generalization ability of learned features for novel objects plays a key role. We propose a new prototype, namely universal prototype, that is learned from all object categories.
  arXiv  Detail & Related papers  (2021-03-01T15:35:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.