Lightweight Remote Sensing Change Detection With Progressive Feature Aggregation and Supervised Attention

Abstract

Remote sensing change detection (RSCD) aims to explore surface changes from co-registered pair of images. However, the high cost of memory and computation in previous CNN-based methods prevent their successes from being applied to real-world applications. Therefore, we propose a novel lightweight network, which identifies changes based on the features extracted by mobile networks via progressive feature aggregation and supervised attention, termed as A2Net. Considering the less powerful representation capability of mobile networks, we design a neighbor aggregation module (NAM) to fuse features within nearby stages of the backbone to strengthen the representation capability of temporal features. Then, we propose a progressive change identifying module (PCIM) to extract temporal difference information from bi-temporal features. Besides, we design a supervised attention module (SAM) to re-weight features for effectively aggregating multi-level features from high levels to low levels. With NAM, PCIM and SAM incorporated, A2Net can achieve favorable results compared with state-of-the-art methods on three challenging RSCD datasets with fewer parameters (3.78M) and lower computation costs (6.02G). The demo code of this work is publicly available at https://github.com/guanyuezhen/ A2Net.