Exploring Conflict-Matching Learning With Temporal Weight-Sharing and Bandwise Spatial-Interacting Transformer for Hyperspectral Change Detection

Hyperspectral imagery is valuable for accurate detection of land-cover changes within a consistent area across time. However, current training paradigms for hyperspectral change detection (CD) are usually in supervised form which are not consistent to heavy labeling cost reality. Moreover, current deep learning methods face limitations due to insufficient temporal dependencies’ sharing and inadequate densely bandwise spatial position dependencies. To tackle these challenges, we introduce an innovative semi-supervised training paradigm called Conflict HyperMatch and a deep learning model called temporal weight-sharing and bandwise spatial interacting transformer (TWBSIT) for hyperspectral CD. The key contributions of this study are as follows: 1) introduction of the Conflict HyperMatch training schedule, which relies on representation discrepancy and weak-to-strong prediction consistency, to improve the sample leveraging of both labeled and unlabeled data; 2) weight-sharing interacting temporal attention (WITA) module is contributed to capture shared temporal interactions and resemblances; and 3) bandwise cross-spatial attention (BCSA) module is introduced to achieve a more extensive spatial perception of the specific central image patch. Extensive experiments conducted on three real datasets validate the effectiveness of the proposed TWBSIT model based on Conflict HyperMatch in leveraging both labeled and unlabeled samples for hyperspectral CD. This method notably decreases the requirement for labeled training samples and surpasses the performance of many existing hyperspectral CD methods.