← Back to all news
arXiv AI By Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera, Selvarajah Thuseethan

HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives

Read the original on arXiv AI →

HiLRP introduces a unified attribution framework for Vision Transformers (ViTs) that addresses the challenges posed by diverse architectural designs. By decomposing ViT operations into four basic types—linear maps, bilinear mixing, normalization/gating, and reindexing—HiLRP applies conservation‑satisfying relevance rules, enabling reliable explanations across a wide range of backbones. The method outperforms 14 existing attribution techniques on 10 architectures, maintaining conservation and improving localization accuracy (0.97 Pointing) compared to competitors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 16

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

The paper introduces ResLRP, an extension of Layer-wise Relevance Propagation that explicitly handles residual connections in Vision Transformers to prevent attribution explosion. It demonstrates that residual cancellation causes instability in ViT explanations, and that ResLRP improves faithfulness and localization across a wide range of ViT architectures, including Vision Language Models. The method also provides a diagnostic measure for predicting attribution degradation and successfully localizes Sparse Autoencoder features.

By Jim Berend, Reduan Achtibat, Daniel Sch\"affer, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer
llmsmultimodalbenchmarks
More like this →