SSI attributes multispectral importance per position via conditional Shapley values
Haotian Ma · hf · 2026-10-22
Spectral-Spatial Interpretation (SSI) from UW-Madison is a full-grid attribution method for multispectral data: for each spatial position, it fixes surrounding context, defines a conditional game over channels, and applies Shapley values — producing a full spectral-spatial attribution matrix instead of a single heatmap or global channel ranking. SSI satisfies Shapley fairness locally, has clear local interpretations, and outperforms existing attribution methods on multispectral image tasks.
More from Research
- ICLR reviewer: 2 of 3 assigned papers are complete AI slop, worst batch ever seen — AkariAsai · 2026-10-22
- Training-free 20B model Viveki generates real-time video heatmaps under 150ms — not-ekalabya · 2026-10-22
- JD paper proposes ROAD MOPD: cross-teacher guarding to fix gradient conflicts in multi-teacher distillation — teortaxesTex · 2026-10-22
- Microsoft's ScholarEvolve lets agents improve by reading papers, lifting Qwen's AppWorld score from 69% to 81.4% — bendee983 · 2026-10-22
- DynaVelo uses neural ODEs to predict gene perturbations that rescue cell mutations — bravo_abad · 2026-10-22
- IBM's LASAGNA study shows RAG technique gains shrink when combined: +47% predicted becomes +17% realized — ibm · 2026-10-22