RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Abstract
Before developing a Document Layout Analysis (DLA) model in real-world applications, conducting comprehensive robustness testing is essential. However, the robustness of DLA models remains underexplored in the literature. To address this, we are the first to introduce a robustness benchmark for DLA models, which includes 450K document images of three datasets. To cover realistic corruptions, we propose a perturbation taxonomy with 36 common document perturbations inspired by real-world document processing. Additionally, to better understand document perturbation impacts, we propose two metrics, Mean Perturbation Effect (mPE) for perturbation assessment and Mean Robustness Degradation (mRD) for robustness evaluation. Furthermore, we introduce a self-titled model, i.e., Robust Document Layout Analyzer (RoDLA), which improves attention mechanisms to boost extraction of robust features. Experiments on the proposed benchmarks (PubLayNet-P, DocLayNet-P, and MDoc-P) demonstrate that RoDLA obtains state-of-the-art mRD scores of 115.7, 135.4, and 150.4, respectively. Compared to previous methods, RoDLA achieves notable improvements in mAP of +3.8%, +7.1% and +12.1%, respectively.
Cite
@article{arxiv.2403.14442,
title = {RoDLA: Benchmarking the Robustness of Document Layout Analysis Models},
author = {Yufan Chen and Jiaming Zhang and Kunyu Peng and Junwei Zheng and Ruiping Liu and Philip Torr and Rainer Stiefelhagen},
journal= {arXiv preprint arXiv:2403.14442},
year = {2024}
}
Comments
Accepted by CVPR 2024. Project page: https://yufanchen96.github.io/projects/RoDLA