Document Layout Analysis on DocLayNet (test)
89mAPDINO (m2doc)
Evaluation results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DINO (m2doc)Modality=Multimodal, Params=256M, Latency=87.25, GFLOPs=7702026.01 | 89 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Cascade (m2doc)Modality=Multimodal, Params=285M, Latency=95.96, GFLOPs=9072026.01 | 86.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PARLModality=Vision-only, Params=65M, Latency=28.65, GFLOPs=2172026.01 | 81.9 | — | — | — | — | — | — | — | — | — | — | — | 93.7 | — | — | — | — | — | — | |
| GLAM + YOLOModel Variant=v5x62023.08 | 80.8 | 77.7 | 77.2 | 66.6 | 86.2 | 86.2 | 78 | 77.1 | 79.8 | 86.3 | 88.1 | 85.1 | — | — | — | — | — | — | — | |
| DFINE-XModality=Vision-only, Params=62M, Latency=22.47, GFLOPs=2022026.01 | 80.7 | — | — | — | — | — | — | — | — | — | — | — | 93.3 | — | — | — | — | — | — | |
| DocLayout-YOLOModality=Vision-only, Params=26M, Latency=13.05, GFLOPs=682026.01 | 79.7 | — | — | — | — | — | — | — | — | — | — | — | 93.4 | — | — | — | — | — | — | |
| DINOModality=Vision-only, Params=67M, Latency=34.89, GFLOPs=2792026.01 | 77.7 | — | — | — | — | — | — | — | — | — | — | — | 93.5 | — | — | — | — | — | — | |
| YOLOV5Backbone=v5x62023.05 | 76.8 | 77.7 | 77.2 | 66.2 | 86.2 | 61.1 | 67.9 | 77.1 | 74.6 | 86.3 | 88.1 | 82.7 | — | — | — | — | — | — | — | |
| YOLOModel Variant=v5x62023.08 | 76.8 | 77.7 | 77.2 | 66.2 | 86.2 | 61.1 | 67.9 | 77.1 | 74.6 | 86.3 | 88.1 | 82.7 | — | — | — | — | — | — | — | |
| CascadeModality=Vision-only, Params=96M, Latency=52.93, GFLOPs=2862026.01 | 75.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LayoutLMv3Modality=Multimodal, Params=133M, GFLOPs=64.82026.01 | 75.4 | — | — | — | — | — | — | — | — | — | — | — | 92.1 | — | — | — | — | — | — | |
| Mask R-CNNBackbone=R1012023.05 | 73.5 | 71.5 | 71.8 | 63.4 | 80.8 | 59.3 | 70 | 72.7 | 69.3 | 82.9 | 85.8 | 80.4 | — | — | — | — | — | — | — | |
| MRCNNBackbone=R1012023.08 | 73.5 | 71.5 | 71.8 | 63.4 | 80.8 | 59.3 | 70 | 72.7 | 69.3 | 82.9 | 85.8 | 80.4 | — | — | — | — | — | — | — | |
| Mask R-CNNModality=Vision-only, Params=63M, Latency=43.08, GFLOPs=2902026.01 | 73.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Faster R-CNNBackbone=R1012023.05 | 73.4 | 70.1 | 73.7 | 63.5 | 81 | 58.9 | 72 | 72 | 68.4 | 82.2 | 85.4 | 79.9 | — | — | — | — | — | — | — | |
| FRCNNBackbone=R1012023.08 | 73.4 | 70.1 | 73.7 | 63.5 | 81 | 58.9 | 72 | 72 | 68.4 | 82.2 | 85.4 | 79.9 | — | — | — | — | — | — | — | |
| Faster R-CNNModality=Vision-only, Params=60M, Latency=26.28, GFLOPs=1812026.01 | 73.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask R-CNNBackbone=R502023.05 | 72.4 | 68.4 | 70.9 | 60.1 | 81.2 | 61.6 | 71.9 | 71.7 | 67.6 | 82.2 | 84.6 | 76.7 | — | — | — | — | — | — | — | |
| MRCNNBackbone=R502023.08 | 72.4 | 68.4 | 70.9 | 60.1 | 81.2 | 61.6 | 71.9 | 71.7 | 67.6 | 82.2 | 84.6 | 76.6 | — | — | — | — | — | — | — | |
| TransDLANetBackbone=R1012023.05 | 72.3 | 68.2 | 74.7 | 61.6 | 81 | 54.8 | 68.2 | 68.5 | 69.8 | 82.4 | 83.8 | 81.7 | — | — | — | — | — | — | — | |
| GLAM2023.08 | 68.6 | 74.3 | 72 | 66.6 | 76.7 | 86.2 | 78 | 5.7 | 79.8 | 56.3 | 74.3 | 85.1 | — | — | — | — | — | — | — | |
| RaV-IDPEntity Class=Table2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | 90.7 | 91.2 | 90.2 | 95.5 | — | — | |
| RaV-IDPEntity Class=Image2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | 77.5 | 82.3 | 73.2 | 92.8 | — | — | |
| RaV-IDPEntity Class=Text2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | 77.8 | 68.5 | 89.9 | 85.3 | — | — | |
| RaV-IDPEntity Class=Formula2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | 0 | — | — | — | — | — | |
| RaV-IDPEntity Class=Micro F1 / Macro F12026.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 78.4 | 61.5 |