DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification

TL;DR

DINO-QPM enhances the interpretability of visual foundation models like DINOv2 by converting complex features into human-understandable, spatially localized representations without retraining the backbone.

Contribution

This work introduces DINO-QPM, a lightweight adapter that makes frozen DINOv2 features globally interpretable and improves explanation quality and accuracy.

Findings

DINO-QPM surpasses DINOv2 linear probe in accuracy.

DINO-QPM provides spatial localization of features within images.

DINO-QPM outperforms other methods in interpretability metrics.

Abstract

Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles for interpretability. This work proposes DINO-QPM, which converts these powerful but entangled features into contrastive, class-independent representations that are interpretable by humans. DINO-QPM is a lightweight interpretability adapter that pursues globally interpretable image classification, adapting the Quadratic Programming Enhanced Model (QPM) to operate on strictly frozen DINO backbones. While classification with visual foundation models typically relies on the \texttt{CLS} token, we deliberately diverge from this standard. By leveraging average-pooling, we directly connect the patch embeddings to the model's features and therefore enable spatial localisation of DINO-QPM's globally interpretable features within the input space. Furthermore, we apply a sparsity loss to minimise spatial scatter and background noise, ensuring that explanations are grounded in relevant object parts. With DINO-QPM we make the level of interpretability of QPM available as an adapter while exceeding the accuracy of DINOv2 linear probe. Evaluated through an introduced Plausibility metric and other interpretability metrics, extensive experiments demonstrate that DINO-QPM is superior to other applicable methods for frozen visual foundation models in both classification accuracy and explanation quality.