Explainability-Driven Dimensionality Reduction for Hyperspectral Imaging
This work addresses computational efficiency and redundancy issues in hyperspectral imaging for material classification, though it is incremental as it applies existing explainability techniques to a known bottleneck.
The study tackled the problem of high dimensionality in hyperspectral imaging by using explainability methods to guide band selection, resulting in classifiers trained on as few as 30 selected bands matching or exceeding full-spectrum baselines while reducing computational requirements.
Hyperspectral imaging (HSI) provides rich spectral information for precise material classification and analysis; however, its high dimensionality introduces a computational burden and redundancy, making dimensionality reduction essential. We present an exploratory study into the application of post-hoc explainability methods in a model--driven framework for band selection, which reduces the spectral dimension while preserving predictive performance. A trained classifier is probed with explanations to quantify each band's contribution to its decisions. We then perform deletion--insertion evaluations, recording confidence changes as ranked bands are removed or reintroduced, and aggregate these signals into influence scores. Selecting the highest--influence bands yields compact spectral subsets that maintain accuracy and improve efficiency. Experiments on two public benchmarks (Pavia University and Salinas) demonstrate that classifiers trained on as few as 30 selected bands match or exceed full--spectrum baselines while reducing computational requirements. The resulting subsets align with physically meaningful, highly discriminative wavelength regions, indicating that model--aligned, explanation-guided band selection is a principled route to effective dimensionality reduction for HSI.