STLNet: Symmetric Transformer Learning Network for Remote Sensing Image Change Detection

Change detection (CD) signifies a pivotal domain within remote sensing image processing. The transformer has been introduced in the field of CD for its global perception capabilities. However, existing transformer-based methodologies serve primarily as mere direct feature extractors, rendering the attention mechanism within the decoder underutilized. To address this, we propose a symmetric transformer learning network (STLNet) specifically tailored for remote sensing image CD tasks, constructed entirely using transformers. The STLNet is designed to leverage the intrinsic capability of transformers to model extensive long-range dependencies effectively. This approach significantly bolsters the extraction of distinctive global-level features, thereby facilitating the accurate delineation of CD regions. Initially, we utilize an adaptive multigrain encoder to extract feature information from bitemporal images, thereby honing the focus on changing targets and providing deeper and more comprehensive information. Subsequently, we adopt an effective decoder architecture comprised of transformer structures, namely, local gather decoder (LGD). The LGD employs a multilevel semantic feature integration from the encoder to augment feature representation and interdependencies, crucial for detailing small changed areas effectively via a hierarchical attentional fusion block. Ultimately, the detection of changes is based on the rich semantic information provided by the LGD, enabling us to achieve enhanced precision in our remote sensing CD efforts. Results show that the proposed STLNet achieved F1 scores of 92.32% on the LEVIR-CD dataset, 90.01% on the WHU-CD dataset, and 82.15% on the SYSU-CD dataset, surpassing mainstream CD methods.