Model card
DAT-DET.
Wan et al. (Baidu)open-sourceUnknown paramsInteractive attention transformer for multi-granularity text detection
Detection head of DAT (Dual-granularity Attention Transformer). Unified model for text at stroke, word, line, paragraph levels. ICML 2024. arxiv:2405.19765
§ 01 · Benchmarks
Every benchmark DAT-DET has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Total-Text | Computer Vision · Scene Text Detection | f-measure | 91.0% | #2 | 2024-05-30 | source ↗ |
| 02 | Total-Text | Computer Vision · Scene Text Detection | precision | 94.0% | #2 | 2024-05-30 | source ↗ |
| 03 | Total-Text | Computer Vision · Scene Text Detection | recall | 88.2% | #3 | 2024-05-30 | 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.
§ 03 · Papers
1 paper with results for DAT-DET.
- 2024-05-30· Computer Vision· 3 results
Towards Unified Multi-granularity Text Detection with Interactive Attention
§ 04 · Related models
Other Wan et al. (Baidu) models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
3 of 3 rows marked verified.