# Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint Evaluation

arXiv: https://arxiv.org/abs/2609.01786 · HTML: https://mlsanity.com/paper/2609.01786/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification](https://mlsanity.com/paper/1902.06701/) (2019)
- [HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model](https://mlsanity.com/paper/2406.11519/) (2024)
- [Do We Train on Test Data? Purging CIFAR of Near-Duplicates](https://mlsanity.com/paper/1902.00423/) (2019)
- [Validating Hyperspectral Image Segmentation](https://mlsanity.com/paper/1811.03707/) (2018)

## Abstract (arXiv)

Hyperspectral image classification still relies heavily on random pixel splits within a single scene. The Salinas dataset, randomly split, is among the most widely used datasets for comparing different architectures. However, under a random split method, a large fraction of test pixels fall immediately adjacent to a training pixel, which inflates reported accuracy. This work introduces a leakage-free evaluation protocol linking spatial separation to the model's receptive field. Applying this protocol across ten different architectures, including classical, spectral, spectral-spatial, transformer, vision-backbone, and state-space families, shows that Macro-F1 drops by 0.147 on average and model rankings change by as many as five places. Furthermore, leakage-free evaluation limits which architectures can be tested on a given benchmark. Since each partition supports patches only within a finite radius, reporting this radius alongside the receptive field is essential for fair comparison. In addition, this study reveals that all ten architectures misclassify largely the same pixels, pointing to a spectral ambiguity in the data that none of them resolves.