cs.CVNov 2, 2026

Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers

Authors: Raphael Maser, Siddhartha Gairola, Sukrut Rao, Bernt Schiele

Organizations: Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany

Abstract

Foundational vision models have become the de facto standard for many vision tasks due to their strong performance. However, they are notoriously opaque and remain hard to interpret. We present ALOE (ALign Once to Explain), a one-time, label-free feature alignment approach that efficiently converts foundational vision models into inherently interpretable B-cos variants. Once aligned, the B-cos backbone is used as a drop-in replacement across several downstream tasks-amortizing the cost of interpretability. ALOE is robust across pre-training paradigms (supervised, self-supervised, vision-language) and can preserve teacher-level generalization with orders of magnitude less data than training from scratch. On classification, it strongly outperforms vanilla B-cosification (e.g., +10.5 p.p. top-1 on ImageNet for DINOv3 ViT-B/16), retains strong linear probing, k-NN, and zero-shot transfer competitive with foundational backbones (DINOv3, SigLIP2) across diverse downstream datasets. It also preserves spatially structured features useful for dense prediction, while yielding well-localized and highly human-interpretable explanations by design.

Figures & tables

Appendix figures & tables22 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Capability ≠\neq Interpretability: Human Interpretability of Vision Foundation Models

    May 19, 2026Julien Colin, Lore Goetschalckx, Nuria Oliver +1Visual Representation LearningVision Foundation Models

  2. Learn to Rank: Visual Attribution by Learning Importance Ranking

    Apr 7, 2026David Schinagl, Christian Fruhwirth-Reisinger, Alexander Prutsch +2Feature AttributionExplainable Image Classification

  3. Language Models Can Explain Visual Features via Steering

    Mar 23, 2026Javier Ferrando, Enrique Lopez-Cuena, Pablo Agustin Martin-Torres +3VLM Interpretability