| SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection | | 90.2 | 90.9 | 89.5 | | SAViL-Det | 2025-07-27 |
| MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild | ✓ Link | 89.8 | 91.4 | 88.3 | 15.2 | MixNet | 2023-08-23 |
| TextMamba: Scene Text Detector with Mamba | | 89.7 | 91.0 | 88.5 | | TextMamba | 2025-12-07 |
| SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression | ✓ Link | 89.6 | 91.6 | 87.7 | | SRFormer (ResNet-50) | 2023-08-21 |
| DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer | ✓ Link | 88.8 | 91.7 | 86.2 | | DPText-DETR (ResNet50) | 2022-07-10 |
| TextFuseNet: Scene Text Detection with Richer Fused Features | ✓ Link | 87.4 | 89.7 | 85.1 | | TextFuseNet (ResNeXt-101) | 2020-05-17 |
| I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection | ✓ Link | 86.5 | 88.4 | 84.6 | | I3CL + SSL | 2021-08-03 |
| Mask R-CNN with Pyramid Attention Network for Scene Text Detection | | 85 | 86.8 | 83.2 | 65.2 | PAN | 2018-11-22 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 84.2 | 87.8 | 80.9 | 66.5 | FAST-B-640 | 2021-11-03 |
| Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network | ✓ Link | 83.7 | 86.4 | 81.2 | | PAN-640 | 2019-08-16 |
| Character Region Awareness for Text Detection | ✓ Link | 83.5 | 86 | 81.1 | | CRAFT | 2019-04-03 |
| Real-time Scene Text Detection with Differentiable Binarization | ✓ Link | 83.4 | | | | DB-ResNet50 (1024) | 2019-11-20 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 82.9 | 85.7 | 80.2 | 92.6 | FAST-B-512 | 2021-11-03 |
| Shape Robust Text Detection with Progressive Scale Expansion Network | ✓ Link | 82.2 | 84.8 | 79.7 | | PSENet-1s | 2019-03-28 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 82 | 85.6 | 78.7 | 112.9 | FAST-S-512 | 2021-11-03 |
| FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation | ✓ Link | 81.5 | 85.5 | 77.9 | 129.1 | FAST-T-512 | 2021-11-03 |
| Shape Robust Text Detection with Progressive Scale Expansion Network | ✓ Link | 81.17 | 82.5 | 79.89 | | PSENet-1s | 2018-06-07 |
| TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes | ✓ Link | 75.6 | 67.9 | 85.3 | | TextSnake | 2018-07-04 |
| Sliding Line Point Regression for Shape Robust Scene Text Detection | ✓ Link | 74.8 | 80.1 | 70.1 | | SLPR | 2018-01-30 |