SOURCE-LINKED INTELLIGENCE

OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdened by complex, multi-stage training pipelines and heavily rely on auxiliary regularization to prevent prototype collapse. To overcome these limitations, we introduce Orthonormal Prototype Alignment Learning (OPAL), a single-stage, end-to-end framework that simplifies interpretable classification. Our approach anchors the latent space using predefined orthonormal bases, embedding each class within a dedicated subspace spanned by fixed part-protot

Read original source ↗ Open in workspace

recordType

paper

region

Global