Model card
DBNet++ (ResNet-18) (1024).
Liao et al.open-sourceUnknown paramsResNet-18 + Differentiable Binarization + Adaptive Scale Fusion
DBNet++ with ResNet-18 backbone at 1024 input size. TPAMI 2022.
§ 01 · Benchmarks
Every benchmark DBNet++ (ResNet-18) (1024) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | CTW1500 | Computer Vision · Scene Text Detection | f-measure | 83.9% | #4 | 2022-02-21 | source ↗ |
| 02 | CTW1500 | Computer Vision · Scene Text Detection | precision | 86.7% | #4 | 2022-02-21 | source ↗ |
| 03 | CTW1500 | Computer Vision · Scene Text Detection | recall | 81.3% | #4 | 2022-02-21 | 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 DBNet++ (ResNet-18) (1024) actually performs.
§ 03 · Papers
1 paper with results for DBNet++ (ResNet-18) (1024).
- 2022-02-21· Computer Vision· 3 results
Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
§ 04 · Related models
Other Liao et al. models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
3 of 3 rows marked verified.