Though vision transformers (ViTs) have achieved state-of-the-art performance
in a variety of settings, they exhibit surprising failures when performing
tasks involving visual relations. This begs the question: how do ViTs attempt
to perform tasks that require computing visual relations between objects? Prior
efforts to interpret ViTs tend to focus on characterizing relevant low-level
visual features. In contrast, we adopt methods from mechanistic
interpretability to study the higher-level visual algorithms that ViTs use to
perform abstract visual reasoning. We present a case study of a fundamental,
yet surprisingly difficult, relational reasoning task: judging whether two
visual entities are the same or different. We find that pretrained ViTs
fine-tuned on this task often exhibit two qualitatively different stages of
processing despite having no obvious inductive biases to do so: 1) a perceptual
stage wherein local object features are extracted and stored in a disentangled
representation, and 2) a relational stage wherein object representations are
compared. In the second stage, we find evidence that ViTs can learn to
represent somewhat abstract visual relations, a capability that has long been
considered out of reach for artificial neural networks. Finally, we demonstrate
that failure points at either stage can prevent a model from learning a
generalizable solution to our fairly simple tasks. By understanding ViTs in
terms of discrete processing stages, one can more precisely diagnose and
rectify shortcomings of existing and future models.

视觉变换器（ViTs）在各种情境下取得了最先进的性能，但在涉及视觉关系的任务中却展现出惊人的失误。本文从机械性可解释性的角度研究了 ViTs 用于执行抽象视觉推理的高层视觉算法，并通过一个关系推理任务的案例研究，发现 ViTs 通常表现出两个完全不同的处理阶段，这些阶段在没有明显的归纳偏差的情况下：1）感知阶段，在此阶段提取并存储局部对象特征，2）关系阶段，在此阶段比较对象表示。通过理解 ViTs 的离散处理阶段，可以更精确地诊断和纠正现有和将来模型的缺陷。