Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Document Layout Analysis
/
PubLayNet val
Document Layout Analysis on PubLayNet val
Metric: Overall (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Overall (best first)
Overall (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Overall
▼
Extra Data
Paper
Date
↕
Code
1
VGT
0.962
No
Vision Grid Transformer for Document Layout Anal...
2023-08-29
Code
2
TRDLU
0.959
No
-
-
-
3
VSR
0.957
No
VSR: A Unified Framework for Document Layout Ana...
2021-05-13
Code
4
DETR
0.957
No
Bridging the Performance Gap between DETR and R-...
2023-06-23
-
5
LayoutLMv3-B
0.951
No
LayoutLMv3: Pre-training for Document AI with Un...
2022-04-18
Code
6
DoPTA
0.949
No
DoPTA: Improving Document Layout Analysis using ...
2024-12-17
-
7
DiT-L
0.949
No
DiT: Self-supervised Pre-training for Document I...
2022-03-04
Code
8
UDoc
0.939
No
Unified Pretraining Framework for Document Under...
2022-04-22
-
9
ResNext-101-32×8d
0.935
No
Vision Grid Transformer for Document Layout Anal...
2023-08-29
Code
10
DeiT-B
0.932
No
Training data-efficient image transformers & dis...
2020-12-23
Code
11
BEiT-B
0.931
No
BEiT: BERT Pre-Training of Image Transformers
2021-06-15
Code
12
Mask RCNN
0.91
No
PubLayNet: largest dataset ever for document lay...
2019-08-16
Code
13
Faster RCNN
0.902
No
PubLayNet: largest dataset ever for document lay...
2019-08-16
Code
14
GLAM
0.722
No
A Graphical Approach to Document Layout Analysis
2023-08-03
Code
#1
VGT
SOTA
0.962
Overall
· 2023-08-29
Vision Grid Transformer for Document Layout Analysis
Code
#2
TRDLU
0.959
Overall
No paper
#3
VSR
SOTA
0.957
Overall
· 2021-05-13
VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations
Code
#4
DETR
0.957
Overall
· 2023-06-23
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images
#5
LayoutLMv3-B
0.951
Overall
· 2022-04-18
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Code
#6
DoPTA
0.949
Overall
· 2024-12-17
DoPTA: Improving Document Layout Analysis using Patch-Text Alignment
#7
DiT-L
0.949
Overall
· 2022-03-04
DiT: Self-supervised Pre-training for Document Image Transformer
Code
#8
UDoc
0.939
Overall
· 2022-04-22
Unified Pretraining Framework for Document Understanding
#9
ResNext-101-32×8d
0.935
Overall
· 2023-08-29
Vision Grid Transformer for Document Layout Analysis
Code
#10
DeiT-B
SOTA
0.932
Overall
· 2020-12-23
Training data-efficient image transformers & distillation through attention
Code
#11
BEiT-B
0.931
Overall
· 2021-06-15
BEiT: BERT Pre-Training of Image Transformers
Code
#12
Mask RCNN
SOTA
0.91
Overall
· 2019-08-16
PubLayNet: largest dataset ever for document layout analysis
Code
#13
Faster RCNN
0.902
Overall
· 2019-08-16
PubLayNet: largest dataset ever for document layout analysis
Code
#14
GLAM
0.722
Overall
· 2023-08-03
A Graphical Approach to Document Layout Analysis
Code