Multi-Temporal Spatial-Spectral Comparison Network for Hyperspectral Anomalous Change Detection

TL;DR

This paper introduces MTC-NET, a deep siamese network utilizing spatial-spectral attention and contrastive learning to improve hyperspectral anomalous change detection by effectively aligning multi-temporal features and suppressing background differences.

Contribution

The paper proposes a novel multi-temporal spatial-spectral comparison network with a specialized attention module for hyperspectral change detection, enhancing feature alignment and background suppression.

Findings

Effective detection of anomalous changes demonstrated on Viareggio 2013 dataset.

Superior performance compared to existing hyperspectral change detection methods.

Robustness to complex imaging conditions and small object changes.

Abstract

Hyperspectral anomalous change detection has been a challenging task for its emphasis on the dynamics of small and rare objects against the prevalent changes. In this paper, we have proposed a Multi-Temporal spatial-spectral Comparison Network for hyperspectral anomalous change detection (MTC-NET). The whole model is a deep siamese network, aiming at learning the prevalent spectral difference resulting from the complex imaging conditions from the hyperspectral images by contrastive learning. A three-dimensional spatial spectral attention module is designed to effectively extract the spatial semantic information and the key spectral differences. Then the gaps between the multi-temporal features are minimized, boosting the alignment of the semantic and spectral features and the suppression of the multi-temporal background spectral difference. The experiments on the "Viareggio 2013" datasets demonstrate the effectiveness of proposed MTC-NET.