Answers are grounded in this paper and cite their sources.
Hyperspectral anomaly detection (HAD) aims to distinguish anomalies from background under an unsupervised paradigm and has been widely used in various fields. Recently, reconstruction-based deep learning methods have attracted considerable attention in HAD, but they have a limitation that anomalies tend to be incorporated into the reconstructed background. To further suppress the reconstruction of anomaly and accurately reconstruct the background, this article proposes a novel multiscale adaptive interaction and wavelet Gaussian attention method for HAD. Specifically, we design a spatial–spectral adaptive interaction attention module to fuse spatial–spectral information and correctly reconstruct background details, and a wavelet-based Gaussian attention module that suppresses anomaly self-reconstruction by exploiting the difference between high-frequency and low-frequency information to better distinguish anomalies from the background. Furthermore, the overall framework employs multiscale encoding and pyramid decoding to ensure effectiveness in various detection scenarios. Extensive experiments on seven hyperspectral datasets demonstrate the superiority of this method.
No takes yet. Share an insight, caveat, or question.
Xu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: