Metric-Driven Attributions for Vision Transformers

Chase Walker, S. Jha, Rickard Ewetz

2/12/2026

No official code found. Best implementation: chasewalker26/MDA-Metric-Driven-Attributions-for-ViT (4 stars, BSD-3-Clause, last commit 2025-10-02).

Semantic Scholar

Code Implementations(1)

chasewalker26/MDA-Metric-Driven-Attributions-for-ViTCommunity67%

BSD-3-Clause

The official implementation of Metric-Driven Attributions for Vision Transformers accepted at ICLR 2025.

41Python, Jupyter NotebookFeb 10, 20251 years agoBSD-3-Clause

Cite this paper

@article{walker2026metricdriven,
  title  = {Metric-Driven Attributions for Vision Transformers},
  author = {Chase Walker and S. Jha and Rickard Ewetz},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:87529758dd31fedc4b75bac475a78609269eb49b},
  journal = {ICLR 2025 2025}
}

Metric-Driven Attributions for Vision Transformers

Code Implementations(1)

Cite this paper

Discussion