Cage and raft aquaculture (CRA) is vital for coastal economy and provides high-quality aquatic products. Accurately monitoring large-scale CRA lays the foundation for predicting CRA product yield and mitigating environmental impacts. This study, focusing on the challenges of detecting large-scale CRA from freely-downloaded, multi-spectral remote sensing imagery due to the complexity of both CRA and marine environment, proposed an attention-fused deep learning model for accurately retrieving large-scale CRA in China's offshore sea using open-source Sentinel-2 (S2) satellite data. We first downloaded the cloud-free preprocessed S2 images in selected study areas. Manual labeling of cage, raft and background areas was performed using high-resolution remote sensing images, with labeled images clipped into 32×32 patches. To enhance the perception ability of feature, the convolutional block attention module was integrated into the well-performing UNet++ by incorporating both channel and spatial attention in each convolutional block of encoder as well as the Level 1 convolutional blocks of decoder. Using the sample dataset in 2021, the proposed AF-UNet++ was trained, and compared to four mainstream convolutional neural networks, and then adopted to map CRA in both 2021 and 2018 in the study areas, as well as four additional sites. Experimental results demonstrate: 1) Our model has the highest OA, F1 and mIoU, with IoU for raft 4.15% higher than other models. 2) Visual comparisons illustrate that AF-UNet++ best excels in extracting CRA. 3) Extraction results both in 2021 and 2018 confirm the proposed model can effectively monitoring large-scale CRA and has the spatio-temporal stability.