Disentangling Visual Transformers: Patch-Level Interpretability for Image Classification

Cite

Text

Jeanneret et al. "Disentangling Visual Transformers: Patch-Level Interpretability for Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.

Markdown

[Jeanneret et al. "Disentangling Visual Transformers: Patch-Level Interpretability for Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/jeanneret2025cvprw-disentangling/)

BibTeX

@inproceedings{jeanneret2025cvprw-disentangling,
  title     = {{Disentangling Visual Transformers: Patch-Level Interpretability for Image Classification}},
  author    = {Jeanneret, Guillaume and Simon, Loïc and Jurie, Frédéric},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2025},
  pages     = {2679-2689},
  url       = {https://mlanthology.org/cvprw/2025/jeanneret2025cvprw-disentangling/}
}