Spatial-Temporal Based Multihead Self-Attention for Remote Sensing Image Change Detection

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 10; pp. 6615 - 6626
• Main Authors: Zhou, Yong, Wang, Fengkai, Zhao, Jiaqi, Yao, Rui, Chen, Silin, Ma, Heping
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: attention mechanism; Building change detection; Change detection; Computer vision; deep learning; Feature extraction; Imaging; Interference; multi-scale; Neural networks; Remote sensing; Task analysis; Transformers
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2022.3176055

The neural network-based remote sensing image change detection method faces a large amount of imaging interference and severe class imbalance problems under high-resolution conditions, which bring new challenges to the accuracy of the detection network. In this work, to address the imaging interference caused by different imaging angles and times, the siamese strategy and multi-head self-attention mechanism are used to reduce the imaging differences between the dual-temporal images and fully exploit the inter-temporal information. Secondly, a learnable multi-part feature learning module is used to adaptively exploit features from different scales to obtain more comprehensive features. Finally, a mixed loss function strategy is used to ensure that the network converges effectively and excludes the adverse interference of a large number of negative samples to the network. Extensive experiments show that our method outperforms numerous methods on LEVIR-CD, WHU, and DSIFN datasets.