Equal is Not Always Fair: A New Perspective on Hyperspectral Representation Non-Uniformity

--Hyperspectral image (HSI) representation is fundamentally challenged by pervasive non-uniformity, where spectral dependencies, spatial continuity, and feature efficiency exhibit complex and often conflicting behaviors. Most existing models rely on a unified processing paradigm that assumes homogeneity across dimensions, leading to suboptimal performance and biased representations. T o address this, we propose FairHyp, a fairness-directed framework that explicitly disentangles and resolves the threefold non-uniformity through cooperative yet specialized modules. We introduce a Runge-Kutta-inspired spatial variability adapter to restore spatial coherence under resolution discrepancies, a multi-receptive field convolution module with sparse-aware refinement to enhance discriminative features while respecting inherent sparsity, and a spectral-context state space model that captures stable and long-range spectral dependencies via bidirectional Mamba scanning and statistical aggregation. Unlike one-size-fits-all solutions, FairHyp achieves dimension-specific adaptation while preserving global consistency and mutual reinforcement. This design is grounded in the view that nonuniformity arises from the intrinsic structure of HSI representations, rather than any particular task setting. T o validate this, we apply FairHyp across four representative tasks including classification, denoising, super-resolution, and inpaintin, demonstrating its effectiveness in modeling a shared structural flaw. Extensive experiments show that FairHyp consistently outperforms state-of-the-art methods under varied imaging conditions. Our findings redefine fairness as a structural necessity in HSI modeling and offer a new paradigm for balancing adaptability, efficiency, and fidelity in high-dimensional vision tasks. YPERSPECTRAL imaging (HSI) provides significantly finer spectral resolution than conventional imaging modalities, demonstrating remarkable and irreplaceable functionality across many fields of application, including medical diagnosis [1], environmental monitoring [2], [3], modern agriculture [4], [5], military and security [6], and beyond. Despite the superior potential, HSI presents unique challenges due to its high-dimensional and complex data structure, requiring specialized processing techniques distinct from traditional images. One of the fundamental challenges in HSI representation learning is inherent non-uniformity, which arises across spectral, spatial, and feature domains. W . Quan and M. Wei are with Nanjing University of Aeronautics and Astronautics, Nanjing, China (e-mail: q.wuzhou@gmail.com; J. Tang is with Nanjing Forestry Univeristy, Nanjing, China (e-mail: tangjh@njfu.edu.cn).