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.
We present HyperImageNet, a large-scale benchmark for fine-grained hyperspectral land-cover understanding. The dataset contains 26,084 airborne hyperspectral image patches with 224 spectral bands and 138 fine-grained land-cover categories. Unlike existing datasets, HyperImageNet provides raw imagery, pixel-level semantic labels, and object-level instance masks, supporting both semantic and instance segmentation. Furthermore, we establish an open-environment benchmark with strict spatial separation to evaluate representative methods and the HyperFree foundation model. Experimental results demonstrate the effectiveness of HyperImageNet for fine-grained hyperspectral understanding and open-environment remote sensing research.
Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We show that this assumption often breaks down in spatiotemporally correlated domains such as aerial surveillance, precision agriculture, and medical imaging, leading to two systematic failures: data leakage, where correlated samples span training and validation splits and inflate performance estimates, and hidden stratification, where errors on minority subpopulations are obscured by aggregate metrics. To address these issues, we propose a unified evaluation and training framework for spatially correlated data. We introduce Structure-Aware Stratified Partitioning (SASP), which constructs validation splits that reduce spatiotemporal leakage while preserving meaningful class balance, and Curriculum Distributionally Robust Optimization (CDRO), a curriculum-based relaxation of distributionally robust training that stabilizes optimization under these stricter splits. Across multiple benchmarks, this combination yields consistently improved generalization, more reliable confidence calibration, and exposes failure modes that remain hidden under conventional random-split evaluation.
Hyperspectral imaging enables fine-grained recognition of materials by capturing rich spectral signatures, but learning robust classifiers is challenging due to high dimensionality, spectral redundancy, limited labeled data, and strong domain shifts. Beyond earth observation, labeled HSI data is often scarce and imbalanced, motivating compact models for generic hyperspectral classification across diverse acquisition regimes. We propose the lightweight Spectral-Spatial Fusion Transformer (SSFT), which factorizes representation learning into spectral and spatial pathways and integrates them via cross-attention to capture complementary wavelength-dependent and structural information. We evaluate our SSFT on the challenging HSI-Benchmark, a heterogeneous multi-dataset benchmark covering earth observation, fruit condition assessment, and fine-grained material recognition. SSFT achieves state-of-the-art overall performance, ranking first while using less than 2% of the parameters of the previous leading method. We further evaluate transfer to the substantially larger SpectralEarth benchmark under the official protocol, where SSFT remains competitive despite its compact size. Ablation studies show that both spectral and spatial pathways are crucial, with spatial modeling contributing most, and that SSFT remains robust without data augmentation.
Alexander Musiat, Nikolas Ebert, Oliver Wasenmüller