ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents

TL;DR

This paper reports on the ICDAR 2023 competition focused on robust layout segmentation in diverse corporate documents, highlighting advances in vision-transformer models and ensemble strategies that improve accuracy and generalization.

Contribution

It introduces a challenging new dataset and benchmark for document layout segmentation, and showcases innovative solutions leveraging recent computer vision techniques.

Findings

Vision-transformer based methods are increasingly adopted.

Ensemble strategies improve segmentation accuracy.

Progress towards robust, generalizable document layout understanding.

Abstract

Transforming documents into machine-processable representations is a challenging task due to their complex structures and variability in formats. Recovering the layout structure and content from PDF files or scanned material has remained a key problem for decades. ICDAR has a long tradition in hosting competitions to benchmark the state-of-the-art and encourage the development of novel solutions to document layout understanding. In this report, we present the results of our \textit{ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents}, which posed the challenge to accurately segment the page layout in a broad range of document styles and domains, including corporate reports, technical literature and patents. To raise the bar over previous competitions, we engineered a hard competition dataset and proposed the recent DocLayNet dataset for training. We recorded 45 team registrations and received official submissions from 21 teams. In the presented solutions, we recognize interesting combinations of recent computer vision models, data augmentation strategies and ensemble methods to achieve remarkable accuracy in the task we posed. A clear trend towards adoption of vision-transformer based methods is evident. The results demonstrate substantial progress towards achieving robust and highly generalizing methods for document layout understanding.