CBW-MSSANet: A CNN Framework With Compact Band Weighting and Multiscale Spatial Attention for Hyperspectral Image Change Detection

Ou, Xianfeng; Liu, Liangzhen; Tu, Bing; Qing, Linbo; Zhang, Guoyun; Liang, Zifei

doi:10.1109/tgrs.2023.3263563

Cited by 7 publications

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [49], cross-temporal attention was designed to explore the temporal change information between bi-temporal features. Ou et al [50] performed attention operations on image patches of different scales at the same time so that the central pixel to be detected in the fused feature map has a higher weight. The Transformer [37] is a network built on the multi-head self-attention (MHSA) mechanism to selectively attend to relevant information and disregard irrelevant input, allowing for it to model long-range dependencies without considering the actual distance.…”

Section: Introductionmentioning

confidence: 99%

Spectral–Temporal Transformer for Hyperspectral Image Change Detection

Ding

2023

Remote Sensing

View full text Add to dashboard Cite

Deep-Learning-based (DL-based) approaches have achieved remarkable performance in hyperspectral image (HSI) change detection (CD). Convolutional Neural Networks (CNNs) are often employed to capture fine spatial features, but they do not effectively exploit the spectral sequence information. Furthermore, existing Siamese-based networks ignore the interaction of change information during feature extraction. To address this issue, we propose a novel architecture, the Spectral–Temporal Transformer (STT), which processes the HSI CD task from a completely sequential perspective. The STT concatenates feature embeddings in spectral order, establishing a global spectrum–time-receptive field that can learn different representative features between two bands regardless of spectral or temporal distance, thereby strengthening the learning of temporal change information. Via the multi-head self-attention mechanism, the STT is capable of capturing spectral–temporal features that are weighted and enriched with discriminative sequence information, such as inter-spectral correlations, variations, and time dependency. We conducted experiments on three HSI datasets, demonstrating the competitive performance of our proposed method. Specifically, the overall accuracy of the STT outperforms the second-best method by 0.08%, 0.68%, and 0.99% on the Farmland, Hermiston, and River datasets, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%