@online{Wrobel2602.06613,
TITLE = {{DAVE}: Distribution-aware Attribution via {ViT} Gradient Decomposition},
AUTHOR = {Wr{\'o}bel, Adam and Gairola, Siddhartha and Tabor, Jacek and Schiele, Bernt and Zieli{\'n}ski, Bartosz and Rymarczyk, Dawid},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2602.06613},
EPRINT = {2602.06613},
EPRINTTYPE = {arXiv},
YEAR = {2026},
ABSTRACT = {Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet producing stable and high-resolution attribution maps for these models remains challenging. Architectural components such as patch embeddings and attention routing often introduce structured artifacts in pixel-level explanations, causing many existing methods to rely on coarse patch-level attributions. We introduce DAVE \textit{(\underline{D}istribution-aware \underline{A}ttribution via \underline{V}iT Gradient D\underline{E}composition)}, a mathematically grounded attribution method for ViTs based on a structured decomposition of the input gradient. By exploiting architectural properties of ViTs, DAVE isolates locally equivariant and stable components of the effective input--output mapping. It separates these from architecture-induced artifacts and other sources of instability.},
}