{"slug": "ten-architectures-one-error-shared-failure-modes-in-hyperspectral-classification", "title": "Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint Evaluation", "summary": "A new arXiv preprint (2609.01786v1) finds that random pixel splits in hyperspectral image classification inflate accuracy, and proposes a leakage-free evaluation protocol linking spatial separation to the model's receptive field. Testing ten architectures on the Salinas dataset, Macro-F1 drops by 0.147 on average and model rankings shift by up to five places, with all architectures misclassifying largely the same pixels due to spectral ambiguity.", "body_md": "arXiv:2609.01786v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/ten-architectures-one-error-shared-failure-modes-in-hyperspectral-classification", "canonical_source": "https://arxiv.org/abs/2609.01786", "published_at": "2026-09-03 04:00:00+00:00", "updated_at": "2026-09-03 04:22:52.784032+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "ai-research"], "entities": ["arXiv", "Salinas dataset"], "alternates": {"html": "https://wpnews.pro/news/ten-architectures-one-error-shared-failure-modes-in-hyperspectral-classification", "markdown": "https://wpnews.pro/news/ten-architectures-one-error-shared-failure-modes-in-hyperspectral-classification.md", "text": "https://wpnews.pro/news/ten-architectures-one-error-shared-failure-modes-in-hyperspectral-classification.txt", "jsonld": "https://wpnews.pro/news/ten-architectures-one-error-shared-failure-modes-in-hyperspectral-classification.jsonld"}}