Two-Level Spectral Adaptation and Multilevel Spectral Evidence Diagnostics for Hyperspectral Remote Sensing Salient Object Detection with a Wavelength-Conditioned Foundation Model

Wavelength-conditioned remote sensing foundation models accept flexible spectral configurations, but compatibility does not ensure effective spectral utilization. We investigate this issue for hyperspectral remote sensing salient object detection and propose SpecAudit, an offline framework diagnosing input discriminability, entry-kernel geometry, and layer-wise spectral readability, together with Two-Level Spectral Adaptation (TLSA). On the 32-band hyperspectral remote sensing salient object detection dataset (HRSSD), expanding a Dynamic One-For-All (DOFA)-based pipeline from 3 to 32 bands yields no stable saliency gain. A ground-truth-assisted image-specific diagnostic readout, fitted and evaluated on spatially separated regions of each test image, yields ΔSα=+0.0418, indicating substantial image-specific spectral discriminability despite the absence of a stable direct prediction gain. TLSA combines task-shared Band Amplitude Calibration, using one learnable gain per band before the frozen entry, with Self-Guided Spectral Refinement, which fits an image-specific spectral discriminant from the coarse prediction at inference. Across five training seeds and paired image-level tests, both adaptation levels provide positive incremental improvements. TLSA increases mean Sα from 0.6472 to 0.6613, yields a positive paired improvement over the three-band reference, and exceeds the highest mean Sα among nine retrained published methods by 3.5%. These results indicate that hyperspectral gains depend on how spectral evidence is exposed and used, not only on available band count. The complete TLSA implementation and SpecAudit diagnostic code will be publicly released upon publication.