A Full-Scale Feature Fusion Siamese Network for Remote Sensing Change Detection

Change detection (CD) is an essential and challenging task in remote sensing image processing. Its performance relies heavily on the exploitation of spatial image information and the extraction of change semantic information. Although some deep feature-based methods have been successfully applied to change detection, most of them use plain encoders to extract the original image features. The plain encoders often have the below disadvantages: (i) the lack of semantic information leads to lower discrimination of shallow features, and (ii) the successive down-sampling leads to less accurate spatial localization of deep features. These problems affect the performance of the network in complex scenes and are particularly detrimental to the detection of small objects and object edges. In this paper, we propose a full-scale feature fusion siamese network (F3SNet), which on one hand enhances the spatial localization of deep features by densely connecting raw image features from shallow to deep layers, and on the other hand, complements the changing semantics of shallow features by densely connecting the concatenated feature maps from deep to shallow layers. In addition, a full-scale classifier is proposed for aggregating feature maps at different scales of the decoder. The full-scale classifier in nature is a variant of full-scale deep supervision, which generates prediction maps at all scales of the decoder and then combines them for the final classification. Experimental results show that our method significantly outperforms other state-of-the-art (SOTA) CD methods, and is particularly beneficial for detecting small objects and object edges. On the LEVIR-CD dataset, our method achieves an F1-score of 0.905 using only 0.966M number of parameters and 3.24 GFLOPs.

Automated summary

This paper proposes a full-scale feature fusion siamese network (F3SNet) that enhances the spatial localization of deep features by densely connecting raw image features and complements the changing semantics of shallow features by densely connecting concatenated feature maps. It also introduces a full-scale classifier for aggregating feature maps at different scales. Experimental results demonstrate its superior performance in change detection, especially for detecting small objects and object edges.