Document Layout Analysis
Analyzing the layout structure of documents
Document Layout Analysis is a key task in computer vision. Below you will find the standard benchmarks used to evaluate models, along with current state-of-the-art results.
Benchmarks & SOTA
publaynet-val
Dataset from Papers With Code
State of the Art
DETR
0.981
table
document-layout-recognition-challenge-test
Dataset from Papers With Code
State of the Art
fglihai
0.970
figure
document-layout-recognition-challenge-mini-dev
Dataset from Papers With Code
State of the Art
fglihai
1
table
u-diads-bib
Dataset from Papers With Code
State of the Art
CV-Group
83.4
class-average-iou
d4la
Dataset from Papers With Code
State of the Art
DoPTA
70.72
map
Related Tasks
General OCR Capabilities
Comprehensive benchmarks covering multiple aspects of OCR performance.
Polish OCR
OCR for Polish language including historical documents, gothic fonts, and diacritic recognition.
Image Classification
Categorizing images into predefined classes (ImageNet, CIFAR).
Object Detection
Locating and classifying objects in images (COCO, Pascal VOC).