AGCDetNet:An Attention-Guided Network for Building Change Detection in High-Resolution Remote Sensing Images

Abstract

While deep learning-based methods have gained considerable improvements in remote sensing (RS) image change detection (CD), scale variations and pseudo-changes hinder most supervised methods' performance. The CD networks derived from other fields can be fronted with false alarms and miss detections in high-resolution RS images due to the weak feature representation ability. In this paper, an attention-guided end-to-end change detection network (AGCDetNet) is proposed based on the fully convolutional network and attention mechanism. AGCDetNet learns to enhance the feature representation of change information and achieve accuracy improvements using spatial-and channelattention. A spatial attention module (SPAM) promotes the discrimination between the changed objects and the background by adding the learned spatial attention to the deep features. Channel-wise attention-guided interference filtering unit (CIFU) / atrous spatial pyramid pooling module (CG-ASPP) enhances the representation of multilevel features and multiscale context, respectively. Extensive experiments have been conducted on several public datasets for performance evaluation, including LEVIR-CD, WHU, Season-Varying, WV2, and ZY3. Experiment results demonstrate that AGCDetNet outperforms several stateof-the-art methods of accuracy and robustness. Specifically, AGCDetNet achieves the best F1-score on two datasets, i.e., LEVIR-CD (0.9076) and Season-Varying (0.9654).

Building change detection using the parallel spatial-channel attention block and edge-guided deep network

“…Moreover, introducing a DE unit improves the efficiency of the network. AGCDetNet (Song and Jiang, 2021) is an attention-guided network for change detection in which multilevel features and multiscale context are enhanced by using spatial attention and a channelwise attention-guided interference filtering unit module. Another comparative method is SNUNet (Fang et al, 2021).…”

Building Change Detection by W-Shape Resunet++ Network With Triple Attention Mechanism

“…They modeled the spatial-temporal relationships by using selfattention mechanism. AGCDetNet (Song and Jiang, 2021) is attention-guided end-to-end change detection network in which multilevel features and multi-scale context are enhance by using spatial attention and channel-wise attention-guided interference filtering unit module.…”

Feature-Guided Multitask Change Detection Network

“…With the widespread application of deep learning [23], [25], [36][37][38] in CD, there has been much research on models [20], [36], data augmentation [25], and loss functions [31], [38]. However, most CD research focuses on binary CD, while few studies focus on multiclass CD and multitask CD.…”

“…For contrastive loss guidance, most CD-related studies [18], [25], [31], [32] adopted cross-entropy loss [33]. There are also some studies that design customized loss functions [34], and a suitable loss function can make the model achieve higher accuracy.…”