Building Change Detection Using Cross-Temporal Feature Interaction Network
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2023)
摘要
Building change detection of remote sensing images is in full flourishing accompanied by the prosperity of convolutional neural networks. For spatial-temporal context modeling, existing solutions disregard the inter-image interactions, albeit their positive contribution to the acquisition of differences. To fill the gap, we propose a cross-temporal feature interaction network to effectively derive the change representations. Specifically, we propose a linearized cross-attention, which motivates each counterpart to glimpse the representation of another image while preserving its own features. In addition, to circumvent the misalignment caused by step-down sampling in the backbone, we introduce multi-level feature alignment using learnable affine transformation and stepwise aggregation. Based on a naive backbone (ResNet18) without sophisticated structures, our model outperforms other state-of-the-art methods on three datasets in terms of both efficiency and effectiveness.
更多查看译文
关键词
Building change detection (BCD),remote sensing (RS),convolutional neural network (CNN),linearized cross-attention,multi-level feature alignment
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要