OpenCodePapers

document-layout-analysis-on-publaynet-val

Document Layout Analysis
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeOverallTextTitleListTableFigureModelNameReleaseDate
Vision Grid Transformer for Document Layout Analysis✓ Link0.9620.9500.9390.9680.9810.971VGT2023-08-29
Transformer-based Approach for Document Understanding0.9590.9580.9210.9750.9760.966TRDLU2022-10-16
VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations✓ Link0.9570.9670.9310.9470.9740.964VSR2021-05-13
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images0.9570.9470.9180.9640.9810.975DETR2023-06-23
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking✓ Link0.9510.9450.9060.9550.9790.970LayoutLMv3-B2022-04-18
DoPTA: Improving Document Layout Analysis using Patch-Text Alignment0.9490.9440.8950.9570.9770.970DoPTA2024-12-17
DiT: Self-supervised Pre-training for Document Image Transformer✓ Link0.9490.9440.8930.9600.9780.972DiT-L2022-03-04
Unified Pretraining Framework for Document Understanding0.9390.9390.8850.9370.9730.964UDoc2022-04-22
Vision Grid Transformer for Document Layout Analysis✓ Link0.9350.9300.8620.9400.9760.968ResNext-101-32×8d2023-08-29
Training data-efficient image transformers & distillation through attention✓ Link0.9320.9340.874 0.9210.9720.957DeiT-B2020-12-23
BEiT: BERT Pre-Training of Image Transformers✓ Link0.9310.9340.8660.9240.973 0.957BEiT-B2021-06-15
PubLayNet: largest dataset ever for document layout analysis✓ Link0.9100.9160.8400.8860.9600.949Mask RCNN2019-08-16
PubLayNet: largest dataset ever for document layout analysis✓ Link0.9020.9100.8260.8830.9540.937Faster RCNN2019-08-16
A Graphical Approach to Document Layout Analysis✓ Link0.7220.8780.8000.8620.8680.206GLAM2023-08-03
CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images✓ Link0.978CDeC-Net2020-08-25