中文

Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models

计算机视觉与模式识别 2026-05-21 v1

摘要

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap with a framework for measuring and comparing the human interpretability of vision models, built around two complementary psychophysics protocols: (1) localizability -- can an observer predict where a feature fires on a novel image? -- and (2) nameability -- can an observer accurately describe what the feature represents? Features are recovered via sparse autoencoders, and a chance-anchored scoring function places every model on a common scale. Applying the framework to six vision transformers -- two supervised ViTs and four foundation models (DINOv2, DINOv3, CLIP, SigLIP) -- we collected more than 15,00015{,}000 behavioral responses, analyzing the 13,40013{,}400 responses from the 377377 participants who passed our pre-specified quality checks. Foundation models are consistently *less* interpretable than their supervised counterparts, and the gap is not a capability tradeoff: interpretability does not correlate with downstream task performance on any benchmark we examine. What does correlate is the locality of a feature's activations and coarse-grained semantic alignment with humans -- models with focal activations and representations that reflect the world's broad categorical structure produce more interpretable features, whereas fine-grained perceptual alignment does not. The two protocols yield strongly correlated rankings and share the same predictors, establishing interpretability as an independent, measurable dimension of representation quality -- and, surprisingly, one on which every foundation model we tested falls below the supervised baselines that came before. Capability alone cannot close that gap; locality and coarse-grained alignment can.

关键词

引用

@article{arxiv.2605.20337,
  title  = {Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models},
  author = {Julien Colin and Lore Goetschalckx and Nuria Oliver and Thomas Serre},
  journal= {arXiv preprint arXiv:2605.20337},
  year   = {2026}
}