Papers › Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
Tianyu Wang, Xiaowei Hu, Chi-Wing Fu, Pheng-Ann Heng
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 fully-convolutional 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.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Instance Shadow Detection | SOBA | SSIS (CVPR 2021) | Asso. AP_bbox | 59.2 | #2 of 3 | Archive leaderboard | report |
| Instance Shadow Detection | SOBA | SSIS (CVPR 2021) | Asso. AP_segm | 52.3 | #2 of 3 | Archive leaderboard | report |
| Instance Shadow Detection | SOBA | SSIS (CVPR 2021) | Bounding Box SOAP | 26.8 | #2 of 3 | Archive leaderboard | report |
| Instance Shadow Detection | SOBA | SSIS (CVPR 2021) | Instance AP_bbox | 41.5 | #2 of 3 | Archive leaderboard | report |
| Instance Shadow Detection | SOBA | SSIS (CVPR 2021) | Instance AP_segm | 43.5 | #2 of 3 | Archive leaderboard | report |
| Instance Shadow Detection | SOBA | SSIS (CVPR 2021) | mask SOAP | 29.9 | #2 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections