Home/Browse/DocLayNet

DocLayNet

Unknown

IBM Research's large-scale document layout analysis dataset with 80,863 annotated pages across 6 document categories: financial reports, scientific papers, patents, government tenders, manuals, and laws & regulations. 11 semantic region labels. The standard benchmark for general-domain document layout segmentation.

Benchmark Stats

Models4
Papers4
Metrics1

SOTA History

Not enough data to show trend.

Only 4 models on this benchmark

Help build the community leaderboard — submit your model results.

mAP

mAP

Higher is better

RankModelSourceScoreYearPaper
1DocFormerv2-Large

DocFormerv2-Large on DocLayNet. 84.1 mAP (COCO-style). Table 2 in DocFormerv2 paper (arXiv 2306.01733, 2023). Adobe Research.

Community84.12026Source
2DiT-L (Cascade R-CNN)

DiT-L with Cascade R-CNN on DocLayNet. 82.6 mAP (COCO-style). Table 4 of DocLayNet paper (arXiv 2206.01062). Best result in the original IBM benchmark paper at publication.

Community82.62026Source
3LayoutLMv3-Large

LayoutLMv3-Large on DocLayNet object detection. 79.5 mAP. Table 3 in LayoutLMv3 paper (arXiv 2204.08387, ACM MM 2022). Microsoft Research.

Community79.52026Source
4DINO (ResNet-50)

DINO detector with ResNet-50 backbone on DocLayNet. 73.4 mAP. Reported in DocLayNet follow-up comparisons as strong detection baseline. arXiv 2203.03605.

Community73.42026Source

Submit a Result