Papers › Learning Semantic Associations for Mirror Detection
Learning Semantic Associations for Mirror Detection
Huankang Guan, Jiaying Lin, Rynson W.H. Lau
Mirrors generally lack a consistent visual appearance, making mirror detection very challenging. Although recent works that are based on exploiting contextual contrasts and corresponding relations have achieved good results, heavily relying on contextual contrasts and corresponding relations to discover mirrors tend to fail in complex real-world scenes, where a lot of objects, e.g., doorways, may have similar features as mirrors. We observe that humans tend to place mirrors in relation to certain objects for specific functional purposes, e.g., a mirror above the sink. Inspired by this observation, we propose a model to exploit the semantic associations between the mirror and its surrounding objects for a reliable mirror localization. Our model first acquires class-specific knowledge of the surrounding objects via a semantic side-path. It then uses two novel modules to exploit semantic associations: 1) an Associations Exploration (AE) Module to extract the associations of the scene objects based on fully connected graph models, and 2) a Quadruple-Graph (QG) Module to facilitate the diffusion and aggregation of semantic association knowledge using graph convolutions. Extensive experiments show that our method outperforms the existing methods and sets the new state-of-the-art on both PMD dataset (f-measure: 0.844) and MSD dataset (f-measure: 0.889).
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Segmentation | MSD (Mirror Segmentation Dataset) | SANet | F-measure | 0.877 | #4 of 5 | Archive leaderboard | report |
| Image Segmentation | MSD (Mirror Segmentation Dataset) | SANet | IoU | 0.798 | #4 of 5 | Archive leaderboard | report |
| Image Segmentation | MSD (Mirror Segmentation Dataset) | SANet | MAE | 0.054 | #4 of 5 | Archive leaderboard | report |
| Image Segmentation | PMD | SANet | F-measure | 0.795 | #3 of 5 | Archive leaderboard | report |
| Image Segmentation | PMD | SANet | IoU | 0.668 | #3 of 5 | Archive leaderboard | report |
| Image Segmentation | PMD | SANet | MAE | 0.032 | #3 of 5 | 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.
Methods
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