SOURCE-LINKED INTELLIGENCE

ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Vision Transformers (ViTs) are central to most modern vision models, yet obtaining input attributions that are fine-grained, faithful, and stable remains challenging. Layer-wise Relevance Propagation (LRP) has been adapted to transformer attention, but in ViTs it often produces noisy, unfaithful explanations. We show that the missing ingredient is the treatment of residual connections: cancellation effects in residual pathways lead to attribution explosion. Moreover, we find that these cancellations are substantially stronger in ViTs than in language transformers. To address this issue, we int

Read original source ↗ Open in workspace

recordType

paper

region

Global