MMFormer: Macro–Micro Transformer for Small-Sample Classification of Mars Hyperspectral Image

Mars hyperspectral image classification (Mars HSIC) provides invaluable information for accurate mineral identification and Martian geology studies. However, this task remains challenging owing to scarce labeled samples, high spectral similarity and environmental noise. Capturing both local details and global contexts is crucial for this task, yet Convolutional Neural Networks struggle with global dependencies, while Transformers tend to neglect fine local details and incur unnecessary computational burden. To address this issue, we propose MMFormer, a Macro-Micro Transformer tailored for Mars HSIC. With a dual-branch architecture, our method adopts themacro-kernel perception and micro-kernel modulationstrategy to synergize global contexts with local details in both spatial and spectral domains. Specifically, the spatial branch adopts macro-kernel perception to capture long-range spatial dependencies, accompanied by micro-kernel modulation for local detail extraction. Meanwhile, the spectral branch utilizes an analogous strategy to perceive long-range spectral correlations and modulate fine-grained spectral variations simultaneously. To mitigate severe background interference, we introduce a Center Prompt Attention (CPA) module that injects a center-focused prompt to adaptively reweight attention toward the central pixel. To integrate these distinct feature representations, a Cross Weighted Fusion (CWF) module is constructed to dynamically fuse complementary spatial and spectral information. Extensive experiments on three Mars hyperspectral datasets demonstrate that MMFormer achieves strong performance and robustness under limited labeled samples and complex environmental conditions. The code is available at RUI-FT/TGRS 2026 MMFormer.