Abstract: ‍ ‍Change detection in remote sensing is a significant research focus within the field. This paper proposes a two-stage feature pyramid-based change detection network to address the challenges of pseudo-change and noise caused by semantic and spatial differences in multi-level features extracted by the encoder. The two-stage decoder was used to enhance the representation of the change feature and suppress the information interference of pseudo-change. First， the Siamese encoder network was used for bi-temporal remote sensing image encoding， feature extraction， and multi-scale initial difference feature extraction. Given the presence of excessive noise and pseudo-change information in the initial difference feature， a first-stage feature pyramid structure and a spatial-channel dual attention fusion mechanism were proposed to facilitate the interaction of semantic information and spatial information in the multi-scale difference feature， relieve the semantic difference and spatial difference of the multi-level feature， initially remove the pseudo-change information interference， and generate a multi-scale initial change feature. Subsequently， to further improve the representation of the change feature and remove the pseudo-change， the second-stage feature pyramid structure was proposed to optimize the multi-scale change feature stage by stage and then predict change detection. Finally， a series of experiments were conducted on two change detection datasets， LEVIR-CD and WHU-CD， and the experimental results proved the effectiveness of the proposed method.