Document Layout Analysis on D4LA
mAP
- 2023-08-29 — VGT: mAP 68.8
- 2024-10-16 — DocLayout-YOLO: mAP 70.3
- 2024-12-17 — DoPTA: mAP 70.72
| Rank | Model | mAP | Model Parameters | Paper | Code | Year |
|---|---|---|---|---|---|---|
| 1 | DoPTA | 70.72 | 85M | DoPTA: Improving Document Layout Analysis using Patch-Text Alignment | 2024 | |
| 2 | DocLayout-YOLO | 70.3 | – | DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception | opendatalab/PDF-Extract-Kit · opendatalab/DocLayout-YOLO | 2024 |
| 3 | VGT | 68.8 | 174M | Vision Grid Transformer for Document Layout Analysis | alibabaresearch/advancedliteratemachinery | 2023 |