Metraipolis › archive › dc_45017ce54fee
MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Models — arXiv:2609.25815
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25815
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:46:41.041Z
- SHA-256 of the archived text
9fc46bb443715adb9a7e5d7f94f964f3fd3cdf3829eaf5830776bd62922836bf- Stable URL of this page
https://metraipolis.com/documento/dc_45017ce54fee
How to cite
MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Models — arXiv:2609.25815 — arXiv (en), https://arxiv.org/abs/2609.25815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45017ce54fee (Metraipolis archive dc_45017ce54fee, sha256 9fc46bb443715adb9a7e5d7f94f964f3fd3cdf3829eaf5830776bd62922836bf)
BibTeX
@misc{dc45017ce54fee,
title = {MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Models — arXiv:2609.25815},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25815},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45017ce54fee; sha256 9fc46bb443715adb9a7e5d7f94f964f3fd3cdf3829eaf5830776bd62922836bf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual attribution methods typically explain predictions using pixels, superpixels, or regular patches. These representations can localize important regions, but provide limited information about their structure. We introduce MorphoSHAP, a model-agnostic post-hoc method that instead uses morphological shapes as the players of a Shapley attribution game. Using the Tree of Shapes, each shape is described by its scale, geometry, and signed contribution, providing explanations of where the evidence lies, what type of structure carries it, and how strongly it affects the prediction. This shared morphological vocabulary enables spatial, textual, and global class-level explanations beyond image-specific heatmaps. To the best of our knowledge, MorphoSHAP is the first SHAP-based image attribution framework to combine these different forms of explanation. Across five diverse datasets and three architectures, MorphoSHAP achieves strong insertion/deletion performance and outperforms competing attribution methods on several benchmarks. Finally, a user study shows that MorphoSHAP provides explanations that are easy to use and are preferred over standard attribution baselines. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.25815 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:18:38.262Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).