A recent class of hyperspectral anomaly detection methods that can be trained once on background datasets and then universally deployed -- without per-scene retraining or parameter tuning -- has demonstrated remarkable efficiency and robustness. Building upon this paradigm, we focus on the integration of spectral and spatial cues and introduce a novel "Rebellious Student" framework for complementary feature learning. Unlike conventional teacher-student paradigms driven by imitation, our method intentionally trains the spatial branch to diverge from the spectral teacher, thereby learning complementary spatial patterns that the teacher fails to capture. A two-stage learning strategy is adopted: (1) a spectral enhancement network is first trained via reverse distillation to obtain robust background spectral representations; and (2) a spatial network -- the rebellious student -- is subsequently optimized using decorrelation losses that enforce feature orthogonality while maintaining reconstruction fidelity to avoid irrelevant noise. Once trained, the framework enhances both spectral and spatial background features, enabling parameter-free and training-free anomaly detection when paired with conventional detectors. Extensive experiments on the HAD100 benchmark show substantial improvements over several established baselines with minimal computational overhead, confirming the effectiveness and generality of the proposed complementary learning paradigm. Our code is publicly available at https://github.com/xjpp2016/FERS.
翻译:近期一类高光谱异常检测方法展现出卓越的效率和鲁棒性,这类方法可在背景数据集上完成一次性训练,随后无需逐场景重新训练或参数调整即可实现通用部署。基于此范式,我们聚焦于光谱与空间线索的融合,提出了一种新颖的“叛逆学生”框架以实现互补特征学习。与传统由模仿驱动的师生范式不同,本方法有意训练空间分支使其偏离光谱教师网络,从而学习教师网络未能捕捉的互补空间模式。我们采用两阶段学习策略:(1) 首先通过反向蒸馏训练光谱增强网络,以获得鲁棒的背景光谱表征;(2) 随后优化空间网络——即“叛逆学生”——通过解相关损失强制特征正交性,同时保持重建保真度以避免无关噪声干扰。训练完成后,该框架可同时增强光谱与空间背景特征,在与传统检测器结合时实现无需参数调整和重新训练的异常检测。在HAD100基准数据集上的大量实验表明,本方法在最小计算开销下较多个现有基线模型取得显著提升,验证了所提互补学习范式的有效性和普适性。代码已公开于https://github.com/xjpp2016/FERS。