arXiv 2610.21114 · cs.LG · 2026-10-15
Spectral-Spatial Interpretation
Haotian Ma, Ruqi Yang, Philip Townsend
Affiliation unverified
In latest · #195 Added on 2026-10-23
One-line takeaway
Spectral-Spatial Interpretation (SSI) computes Shapley values over channels at each position of multispectral images, yielding a full position × channel attribution matrix instead of a single heatmap or global channel ranking.
SSI（光谱-空间解释）针对多光谱图像，在每个像素位置对各通道单独计算 Shapley 值，得到完整的“位置×通道”归因矩阵，而不是单张热力图或全局通道排名。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Vision & 3D
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲187
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲170
- DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations ▲129
- GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed ▲94
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-23.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.