Answers are grounded in this paper and cite their sources.
Pixel-level annotation of hyperspectral images is expensive and time-consuming, making few-shot hyperspectral image classification (HSIC) a challenging task. Existing few-shot HSIC methods mainly exploit spatial–spectral representations, while frequency domain cues remain insufficiently explored. Moreover, conventional frequency domain methods usually rely on fixed transformations, limiting their flexibility in modeling complex intraclass variations under limited supervision. To address these limitations, this article proposes S2FNet, a spatial–spectral–frequency learning framework that introduces learnable frequency prompts to adaptively modulate frequency representations for few-shot HSIC. First, a frequency domain prompt pool mechanism is designed to adaptively select relevant frequency subprompts to learn discriminative frequency representations. Second, a multiscale frequency domain reconstruction module is constructed to effectively integrate high-level semantic information and low-level spatial textures across frequency sub-bands of different scales. Finally, a dual-stream spectral-frequency enhancement module is designed to model frequency responses along the spectral dimension and enhance informative spectral bands. Experimental results on various public datasets demonstrate that S2FNet achieves competitive classification accuracy and computational efficiency compared with existing advanced methods.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: