Hyperspectral Anomaly Detection (HAD) aims to detect the pixel or target whose spectral characteristics are significantly different from surrounding pixels targets. The effectiveness of reconstructing background model is an essential element affecting improvement HAD performance. This paper proposes a method based on Attention-aware Spectral Difference Representation (HAD-ASDR) reconstruct more...

Hyperspectral image (HSI) denoising based on nonlocal subspace representation has attracted a lot of attention recently. However, most the existing works mainly focus refining coefficient images (RCIs) using certain denoiser but ignore understanding why these pseudoimages have similar spatial structure as original HSI. In this work, we revisit such vein from respective principal component analy...