MMR-HAD: Multi-scale Mamba Reconstruction Network for Hyperspectral Anomaly Detection

Hyperspectral anomaly detection (HAD) aims to identify anomalous objects from hyperspectral images (HSIs) whose spectral features significantly deviate from their surroundings. Existing HAD methods still reconstruct some anomalies during the background reconstruction process, which can seriously affect the detection accuracy. Consequently, inspired by Mamba’s ability to effectively model long sequences, we propose a Multi-scale Mamba Reconstruction Network for Hyperspectral Anomaly Detection (MMR-HAD) by enhancing the representation of the background and inhibit anomalies from being reconstructed. MMR-HAD first removes most of the anomalous pixels in hyperspectral images using the Random Mask (RM) strategy, which reduces the interference of anomalous pixels on the background reconstruction and makes the background features more prominent. To further filter out the small amount of residual anomalous pixels, we propose the Multi-scale Dilated Attention Background Enhancement (MDABE) mechanism, which enhances the background representation. Finally, we apply the Multi-scale Dynamic Feature Fusion (MDFF) strategy to reconstruct the background image, further extracting and strengthening the background information, thus obtaining a pure background image. MMR-HAD, which focuses on generating a pure background, has been experimentally validated on seven real hyperspectral datasets. The results demonstrate that it excels in background enhancement and anomaly suppression, significantly improving detection accuracy. Introducing Mamba offers a promising solution for HAD, with substantial potential for practical application.