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

arXiv: https://arxiv.org/abs/2505.11267 · HTML: https://mlsanity.com/paper/2505.11267/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 73 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 23 of 23)

- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Three dimensional Deep Learning approach for remote sensing image classification](https://mlsanity.com/paper/1806.05824/) (2018)
- [Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery](https://mlsanity.com/paper/2005.08752/) (2020)
- [3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising](https://mlsanity.com/paper/2003.04547/) (2020)
- [Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration](https://mlsanity.com/paper/2010.12921/) (2020)
- [Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations](https://mlsanity.com/paper/2103.06842/) (2021)
- [Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution](https://mlsanity.com/paper/1902.00301/) (2019)
- [Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising](https://mlsanity.com/paper/2304.00844/) (2023)
- [A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration](https://mlsanity.com/paper/2111.09708/) (2021)
- [Spatial-Spectral Transformer for Hyperspectral Image Denoising](https://mlsanity.com/paper/2211.14090/) (2022)
- [Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey](https://mlsanity.com/paper/1708.05125/) (2017)
- [Weighted Low-rank Tensor Recovery for Hyperspectral Image Restoration](https://mlsanity.com/paper/1709.00192/) (2017)
- [ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2307.14010/) (2023)
- [Deep Hyperspectral Unmixing using Transformer Network](https://mlsanity.com/paper/2203.17076/) (2022)
- [Hybrid Spectral Denoising Transformer with Guided Attention](https://mlsanity.com/paper/2303.09040/) (2023)
- [Spectral Unmixing via Data-guided Sparsity](https://mlsanity.com/paper/1403.3155/) (2014)
- [Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2205.14887/) (2022)
- [Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken](https://mlsanity.com/paper/2407.07307/) (2024)
- [Dual Selective Fusion Transformer Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2410.03171/) (2024)
- [Deep Diversity-Enhanced Feature Representation of Hyperspectral Images](https://mlsanity.com/paper/2301.06132/) (2023)
- [Physics-Inspired Degradation Models for Hyperspectral Image Fusion](https://mlsanity.com/paper/2402.02411/) (2024)

## Abstract (arXiv)

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.