Abstract: Shadow detection is always a basic challenge in the computer vision area. It needs an understanding of global image semantic and local detail information. In this paper, we proposed a novel Prior Feature Pyramid Network for shadow detection. The framework constructed the prior attention module to extract the shadow prior information and employed it to weigh convolutional features to guide the network to learn shadow regions. Meanwhile, we also applied a feature polymerization module to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway and used post-process operation to help the network optimize prediction results. We employed two common shadow detection benchmark datasets and perform experiments to evaluate our network. Experiment results show that our proposed approach can more accurately detect the shadow regions with sharpened details and hence substantially improve the performance compared to the previous state-of-the-arts. Our approach achieves excellent performance with 96.6% accuracy value and 6.22 balance error rate on the SBU dataset.