# Adaptive Band Selection for Hyperspectral Classification with Spatially Disjoint Evaluation

arXiv: https://arxiv.org/abs/2606.06684 · HTML: https://mlsanity.com/paper/2606.06684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 5 of 5)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral Image](https://mlsanity.com/paper/1904.08269/) (2019)
- [On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification](https://mlsanity.com/paper/1605.05829/) (2016)
- [Dropout Concrete Autoencoder for Band Selection on HSI Scenes](https://mlsanity.com/paper/2401.16522/) (2024)

## Abstract (arXiv)

Hyperspectral band selection methods based on differentiable selectors can be sensitive to initialization and to extracting a final discrete subset, while prescribed band counts limit flexibility. We propose SGBR-HC (Spectral-Group Band Ranking with Hard-Concrete initialization), a two-stage method that uses a supervised spectral ranking to initialize trainable sparse gates rather than treating ranking as a fixed selection rule, letting the number of selected bands be determined by training. Stage-1 scores candidate bands from training pixels by class discriminability and spectral diversity; this ranking seeds the gate logits for Stage-2, which trains the sparse gates jointly with a spatial classifier. Under spatially disjoint evaluation on Pavia University and Houston 2013, verified by retraining a fresh classifier on the selected bands, SGBR-HC achieves the highest mean overall accuracy and Cohen's kappa with approximately twenty bands. Bypassing Stage-1 degrades OA by 8.84 pp on Pavia University and 22.15 pp on Houston 2013, confirming the ranking prior's role. Random pixel splits inflate OA on Pavia University by 30.56 pp, underscoring spatial leakage as a critical evaluation confound.