Model card
TextBPN++ (ResNet-18).
Zhang et al.open-sourceUnknown paramsResNet-18 + Boundary Transformer
TextBPN++ lightweight variant with ResNet-18 backbone. Accepted IEEE Transactions on Multimedia 2023. arxiv:2205.05320.
§ 01 · Benchmarks
Every benchmark TextBPN++ (ResNet-18) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | msra-td500 | Computer Vision · Scene Text Detection | f-measure | 89.8% | #3 | 2022-05-11 | source ↗ |
| 02 | msra-td500 | Computer Vision · Scene Text Detection | precision | 92.4% | #3 | 2022-05-11 | source ↗ |
| 03 | msra-td500 | Computer Vision · Scene Text Detection | recall | 87.5% | #3 | 2022-05-11 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where TextBPN++ (ResNet-18) actually performs.
§ 03 · Papers
1 paper with results for TextBPN++ (ResNet-18).
- 2022-05-11· Computer Vision· 3 results
Arbitrary Shape Text Detection via Boundary Transformer
§ 04 · Related models
Other Zhang et al. models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
3 of 3 rows marked verified.