Low-rank and sparse representation meet deep unfolding: a new interpretable network for hyperspectral change detection.

Zhou, Chengle; He, Zhi; Dong, Jian; Li, Yunfei; Ren, Jinchang; Plaza, Antonio

Abstract

Hyperspectral image change detection (HSI-CD) is a technique that intelligently checks the changed details in bitemporal hyperspectral images (Bi-HSIs). Deep learning (DL), with the ability to model nonlinear changing features, has achieved promising results in HSI-CD, but the feature mining mechanism is unclear and the architecture design lacks transparency in such DL models. To alleviate this problem, this paper proposes a new low-rank and sparse representation-based deep unfolding network (LRSRNet) for HSI-CD. For feature mining mechanism, the LRSRNet adopts a low-rank and sparse subnetwork (LRSnet) and a change detection sub-network (CDnet). The former is responsible for extracting low-rank features with valuable information and suppressing sparse features containing interference information, while the latter aims to obtain change information from low-rank features. For architecture design, the LRSnet formulates the HSI as a low-rank estimation, sparse estimation, and hyperspectral reconstruction in a low-rank and sparse model, and iteratively optimizes and updates the above sub-problems through deep networks. A new CDnet is designed as a concise convolutional architecture to extract change information from representative Bi-HSIs features. Experiments on three real datasets demonstrate the performance superiority of the proposed LRSRNet method over nine model-driven, datadriven, and model-data-joint-driven HSI-CD algorithms in both qualitative and quantitative evaluations. The proposed LRSRNet is available online: https://github.com/chengle-zhou/LRSRNet.

Citation

ZHOU, C., HE, Z., DONG, J., LI, Y., REN, J. and PLAZA, A. 2025. Low-rank and sparse representation meet deep unfolding: a new interpretable network for hyperspectral change detection. IEEE transactions on geoscience and remote sensing [online], Early Access. Available from: https://doi.org/10.1109/TGRS.2025.3564996

• Journal Article Type: Article
• Acceptance Date: May 12, 2025
• Online Publication Date: May 12, 2025
• Deposit Date: May 16, 2025
• Publicly Available Date: May 16, 2025
• Journal: IEEE transactions on geoscience and remote sensing
• Print ISSN: 0196-2892
• Electronic ISSN: 1558-0644
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/tgrs.2025.3564996
• Keywords: Bi-temporal hyperspectral images; Change detection; Deep unfolding; Low-rank and sparse representation
• Public URL: https://rgu-repository.worktribe.com/output/2836717