Single-Stage Instance Shadow Detectionwith Bidirectional Relation Learning
PubDate: June 2021
Teams: 1 Department of Computer Science and Engineering, The Chinese University of Hong Kong 2 Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
Writers: Tianyu Wang1,∗, Xiaowei Hu1,∗,†, Chi-Wing Fu1, and Pheng-Ann Heng1,2
Instance shadow detection aims to find shadow instances paired with the objects that cast the shadows. The previous work adopts a two-stage framework to first predict shadow instances, object instances, and shadow-object associations from the region proposals, then leverage a post-processing to match the predictions to form the final shadow-object pairs. In this paper, we present a new single-stage fullyconvolutional network architecture with a bidirectional relation learning module to directly learn the relations of shadow and object instances in an end-to-end manner. Compared with the prior work, our method actively explores the internal relationship between shadows and objects to learn a better pairing between them, thus improving the overall performance for instance shadow detection. We evaluate our method on the benchmark dataset for instance shadow detection, both quantitatively and visually. The experimental results demonstrate that our method clearly outperforms the state-of-the-art method.