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

TL;DR

This paper introduces FairHyp, a novel framework for hyperspectral image representation that explicitly addresses non-uniformity across spectral, spatial, and feature dimensions, improving performance across multiple tasks.

Contribution

FairHyp is the first model to disentangle and adapt to the threefold non-uniformity in hyperspectral images through specialized modules, enhancing accuracy and robustness.

Findings

Outperforms state-of-the-art methods in classification, denoising, super-resolution, and inpainting.

Effectively models complex spectral and spatial dependencies in hyperspectral data.

Demonstrates the importance of structural fairness in high-dimensional vision tasks.

Abstract

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. To 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 non-uniformity arises from the intrinsic structure of HSI representations, rather than any particular task setting. To 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.