Research map / Detection and segmentation / CNN features
Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
Shi-Xue Zhang, Xiaobin Zhu, Chun Yang, Hongfa Wang, Xu-Cheng Yin
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use adaptive RNN+GCN encoder instead of RNN (ablation) | deformation model · Total-Text | F-measure: 85.93 -> 86.87 | Improved |
| use adaptive RNN+GCN encoder instead of graph convolution (ablation) | deformation model · Total-Text | F-measure: 86.19 -> 86.87 | Improved |
| use adaptive RNN+GCN encoder instead of FC (ablation) | deformation model · CTW-1500 | F-measure: 81.54 -> 83.97 | Improved |
| use adaptive encoder instead of circular convolution (ablation) | deformation model · CTW-1500 | F-measure: 82.55 -> 83.97 | Improved |
| use adaptive encoder instead of RNN (ablation) | deformation model · CTW-1500 | F-measure: 83.56 -> 83.97 | Improved |
| add distance field to classification map (ablation) | prior information · Total-Text | F-measure: 79.87 -> 85.32 | Improved |
| add direction field to classification and distance (ablation) | prior information · Total-Text | F-measure: 85.32 -> 86.87 | Improved |
| increase inference iterations from 1 to 3 (ablation) | boundary deformation · CTW-1500 | F-measure: 82.24 -> 83.97 | Improved |
| increase inference iterations from 1 to 3 (ablation) | boundary deformation · CTW-1500 | FPS: 13.68 -> 12.08 | Hurt |
| increase iterations from 2 to 3 (ablation) | boundary deformation · CTW-1500 | F-measure: 83.33 -> 83.97 | No clear effect |
| use higher-resolution FPN features (1/1 vs 1/4) (ablation) | shared features · Total-Text | F-measure: 86.13 -> 86.87 | Improved |
| use higher-resolution FPN features (1/1 vs 1/4) (ablation) | shared features · Total-Text | FPS: 15.17 -> 10.56 | Hurt |
Closest papers by meaning
- Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (CVPR 2019 · similarity 0.90)
- ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection (CVPR 2020 · similarity 0.89)
- Progressive Contour Regression for Arbitrary-Shape Scene Text Detection (CVPR 2021 · similarity 0.88)
- Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection (CVPR 2020 · similarity 0.88)
- CPN: Complementary Proposal Network for Unconstrained Text Detection (AAAI 2024 · similarity 0.88)
- LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
