HAPPI: Hyperbolic Hierarchical Part Prototypes for Image Recognition

Hooman Vaseli, Victoria Wu, Nima Kondori, Nguyen Nhat Minh To, Andrea Fung, Ang Nan Gu, Purang Abolmaesumi

Keywords: Explainable AI, Prototype Part Networks, Hyperbolic Embedding Space

TL;DR: HAPPI organizes prototypes hierarchically in hyperbolic space, where localized generic features near the origin and broader specific features farther away enhance part-based classification while matching Euclidean approaches.

Abstract: Prototypical part networks have gained prominence in computer vision due to their inherent interpretability, enabling decisions based on representative part features without post-hoc explanations. However, existing prototypical networks learn part-based features in flat Euclidean space, yet they could better capture the natural hierarchical relationships within image features to enhance performance on tasks requiring structural understanding. To address this opportunity, we propose HAPPI (Hierarchical And Part Prototypical Image recognition), a framework that leverages hyperbolic geometry to organize prototypical part features hierarchically within a Lorentzian manifold. By arranging localized generic features near the hyperboloid origin and broader specific features farther away, HAPPI learns generic prototypes for defining local patterns and specific prototypes that aggregate broader discriminative cues, effectively capturing hierarchy in image data. Our approach is model-agnostic and can be applied to various prototypical neural networks and backbones. We evaluate HAPPI on several baselines and datasets, showing that hyperbolic prototypes match or outperform Euclidean ones while adding interpretability. Qualitative results reveal that generic prototypes highlight localized, class-defining traits, while specific prototypes capture broader patterns across larger regions, enabling differentiation through both local and contextual features. Our code can be found at http://github.com/DeepRCL/HAPPI.

Track: Full paper (8 pages excluding references, same as main conference requirements)

Git: https://github.com/DeepRCL/HAPPI

Submission Number: 11