Causal Attribution via Activation Patching
This work addresses the problem of interpretability for Vision Transformers, providing more accurate attributions for researchers and practitioners, though it is incremental as it builds on existing attribution techniques.
The paper tackled the challenge of producing faithful and localized attributions for Vision Transformers by proposing Causal Attribution via Activation Patching (CAAP), which directly intervenes on internal activations to estimate patch contributions, resulting in significantly outperforming existing methods across multiple backbones and metrics.
Attribution methods for Vision Transformers (ViTs) aim to identify image regions that influence model predictions, but producing faithful and well-localized attributions remains challenging. Existing gradient-based and perturbation-based techniques often fail to isolate the causal contribution of internal representations associated with individual image patches. The key challenge is that class-relevant evidence is formed through interactions between patch tokens across layers, and input-level perturbations can be poor proxies for patch importance, since they may fail to reconstruct the internal evidence actually used by the model. We propose Causal Attribution via Activation Patching (CAAP), which estimates the contribution of individual image patches to the ViT's prediction by directly intervening on internal activations rather than using learned masks or synthetic perturbation patterns. For each patch, CAAP inserts the corresponding source-image activations into a neutral target context over an intermediate range of layers and uses the resulting target-class score as the attribution signal. The resulting attribution map reflects the causal effect of patch-associated internal representations on the model's prediction. The causal intervention serves as a principled measure of patch influence by capturing class-relevant evidence after initial representation formation, while avoiding late-layer global mixing that can reduce spatial specificity. Across multiple ViT backbones and standard metrics, CAAP significantly outperforms existing methods and produces more faithful and localized attributions.