Papers › Mask R-CNN with Pyramid Attention Network for Scene Text Detection
Mask R-CNN with Pyramid Attention Network for Scene Text Detection
Zhida Huang, Zhuoyao Zhong, Lei Sun, Qiang Huo
In this paper, we present a new Mask R-CNN based text detection approach which can robustly detect multi-oriented and curved text from natural scene images in a unified manner. To enhance the feature representation ability of Mask R-CNN for text detection tasks, we propose to use the Pyramid Attention Network (PAN) as a new backbone network of Mask R-CNN. Experiments demonstrate that PAN can suppress false alarms caused by text-like backgrounds more effectively. Our proposed approach has achieved superior performance on both multi-oriented (ICDAR-2015, ICDAR-2017 MLT) and curved (SCUT-CTW1500) text detection benchmark tasks by only using single-scale and single-model testing.
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 |
|---|---|---|---|---|---|---|---|
| Scene Text Detection | ICDAR 2015 | PAN | F-Measure | 85.9 | #22 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | PAN | Precision | 90.8 | #22 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | PAN | Recall | 81.5 | #22 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2017 MLT | PAN | F-Measure | 74.3% | #9 of 14 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2017 MLT | PAN | Precision | 80 | #9 of 14 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2017 MLT | PAN | Recall | 69.8 | #9 of 14 | Archive leaderboard | report |
| Scene Text Detection | SCUT-CTW1500 | PAN | F-Measure | 85 | #6 of 17 | Archive leaderboard | report |
| Scene Text Detection | SCUT-CTW1500 | PAN | FPS | 65.2 | #6 of 17 | Archive leaderboard | report |
| Scene Text Detection | SCUT-CTW1500 | PAN | Precision | 86.8 | #6 of 17 | Archive leaderboard | report |
| Scene Text Detection | SCUT-CTW1500 | PAN | Recall | 83.2 | #6 of 17 | 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