Model card
HTBNet (ResNet-50).
Chen et al.open-sourceUnknown paramsResNet-50 + Hyperbolic Tangent Binarization + MSCA + FMCS
Arbitrary shape scene text detection with Hyperbolic Tangent Binarization (HTB) and Cross-Entropy loss. Multi-Scale Channel Attention (MSCA) and Fused Module with Channel and Spatial (FMCS). MDPI Entropy 2024. DOI:10.3390/e26070560.
§ 01 · Benchmarks
Every benchmark HTBNet (ResNet-50) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | msra-td500 | Computer Vision · Scene Text Detection | precision | 92.2% | #4 | 2024-06-29 | source ↗ |
| 02 | msra-td500 | Computer Vision · Scene Text Detection | f-measure | 87.5% | #5 | 2024-06-29 | source ↗ |
| 03 | msra-td500 | Computer Vision · Scene Text Detection | recall | 83.3% | #7 | 2024-06-29 | 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 HTBNet (ResNet-50) actually performs.
§ 03 · Papers
1 paper with results for HTBNet (ResNet-50).
- 2024-06-29· Computer Vision· 3 results
HTBNet: Arbitrary Shape Scene Text Detection with Binarization of Hyperbolic Tangent and Cross-Entropy
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
3 of 3 rows marked verified.