Metraipolis › archive › dc_e1db23444ced

Spectral-Spatial Interpretation — arXiv:2610.21114

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21114
License (as archived)
CC0-1.0
Archived
2026-10-16T10:20:09.341Z
SHA-256 of the archived text
25757d4bbd13de705ebc2680595acd418319c3e186a1cdb8b4c4f4ad274f7f2e
Stable URL of this page
https://metraipolis.com/documento/dc_e1db23444ced

How to cite

Spectral-Spatial Interpretation — arXiv:2610.21114 — arXiv (en), https://arxiv.org/abs/2610.21114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1db23444ced (Metraipolis archive dc_e1db23444ced, sha256 25757d4bbd13de705ebc2680595acd418319c3e186a1cdb8b4c4f4ad274f7f2e)
BibTeX
@misc{dce1db23444ced,
  title = {Spectral-Spatial Interpretation — arXiv:2610.21114},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21114},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1db23444ced; sha256 25757d4bbd13de705ebc2680595acd418319c3e186a1cdb8b4c4f4ad274f7f2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. These separate views are limiting for multispectral data because channel relevance is often spatially localized and physically meaningful. We introduce Spectral-Spatial Interpretation (SSI), a full-grid attribution method over position-channel players (g,c). For each spatial position, SSI fixes the observed surrounding context, defines a conditional game over the channels at that position, and applies the Shapley value to this local game. The result is a full spectral-spatial attribution matrix rather than a single heatmap or a global channel ranking. SSI has a clear local interpretation. It satisfies Shapley fairness within each position, and aggregating its channel attributions exactly recovers the position-level contextual contrast obtained by replacing that position with the baseline. SSI also differs from context-averaged Owen-style hierarchical accounting, which uses the same position-channel grouping but averages over external spatial coalitions. On HLS Burn Scar, SSI outperforms an MC-Owen estimator across retained attribution metrics while using only about 6% of its evaluation budget. Across CUB-200, EuroSAT, and HLS Burn Scar under both per-channel mean and zero baselines, SSI achieves the best joint deletion and insertion AUC over dense, flat, and rank-1 baselines, yields the strongest spectral hit rates and channel deletion, and leads spatial localization on both annotated datasets. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21114 — 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 2026-10-16T08:48:02.681Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).