Document Layout Analysis on PubLayNet val

Metric: Figure (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Figure▼	Extra Data	Paper	Date↕	Code
1	DETR	0.975	No	Bridging the Performance Gap between DETR and R-...	2023-06-23	-
2	DiT-L	0.972	No	DiT: Self-supervised Pre-training for Document I...	2022-03-04	Code
3	VGT	0.971	No	Vision Grid Transformer for Document Layout Anal...	2023-08-29	Code
4	LayoutLMv3-B	0.97	No	LayoutLMv3: Pre-training for Document AI with Un...	2022-04-18	Code
5	DoPTA	0.97	No	DoPTA: Improving Document Layout Analysis using ...	2024-12-17	-
6	ResNext-101-32×8d	0.968	No	Vision Grid Transformer for Document Layout Anal...	2023-08-29	Code
7	TRDLU	0.966	No	-	-	-
8	VSR	0.964	No	VSR: A Unified Framework for Document Layout Ana...	2021-05-13	Code
9	UDoc	0.964	No	Unified Pretraining Framework for Document Under...	2022-04-22	-
10	DeiT-B	0.957	No	Training data-efficient image transformers & dis...	2020-12-23	Code
11	BEiT-B	0.957	No	BEiT: BERT Pre-Training of Image Transformers	2021-06-15	Code
12	Mask RCNN	0.949	No	PubLayNet: largest dataset ever for document lay...	2019-08-16	Code
13	Faster RCNN	0.937	No	PubLayNet: largest dataset ever for document lay...	2019-08-16	Code
14	GLAM	0.206	No	A Graphical Approach to Document Layout Analysis	2023-08-03	Code

#1DETRSOTA
0.975
Figure· 2023-06-23
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images
#2DiT-LSOTA
0.972
Figure· 2022-03-04
DiT: Self-supervised Pre-training for Document Image Transformer Code
#3VGT
0.971
Figure· 2023-08-29
Vision Grid Transformer for Document Layout Analysis Code
#4LayoutLMv3-B
0.97
Figure· 2022-04-18
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking Code
#5DoPTA
0.97
Figure· 2024-12-17
DoPTA: Improving Document Layout Analysis using Patch-Text Alignment
#6ResNext-101-32×8d
0.968
Figure· 2023-08-29
Vision Grid Transformer for Document Layout Analysis Code
#7TRDLU
0.966
Figure
No paper
#8VSRSOTA
0.964
Figure· 2021-05-13
VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations Code
#9UDoc
0.964
Figure· 2022-04-22
Unified Pretraining Framework for Document Understanding
#10DeiT-BSOTA
0.957
Figure· 2020-12-23
Training data-efficient image transformers & distillation through attention Code
#11BEiT-B
0.957
Figure· 2021-06-15
BEiT: BERT Pre-Training of Image Transformers Code
#12Mask RCNNSOTA
0.949
Figure· 2019-08-16
PubLayNet: largest dataset ever for document layout analysis Code
#13Faster RCNN
0.937
Figure· 2019-08-16
PubLayNet: largest dataset ever for document layout analysis Code
#14GLAM
0.206
Figure· 2023-08-03
A Graphical Approach to Document Layout Analysis Code