RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914723257122816 |
|---|---|
| author | Chen, Yufan Zhang, Jiaming Peng, Kunyu Zheng, Junwei Liu, Ruiping Torr, Philip Stiefelhagen, Rainer |
| author_facet | Chen, Yufan Zhang, Jiaming Peng, Kunyu Zheng, Junwei Liu, Ruiping Torr, Philip Stiefelhagen, Rainer |
| contents | 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 M$^6$Doc-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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14442 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RoDLA: Benchmarking the Robustness of Document Layout Analysis Models Chen, Yufan Zhang, Jiaming Peng, Kunyu Zheng, Junwei Liu, Ruiping Torr, Philip Stiefelhagen, Rainer Computer Vision and Pattern Recognition 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 M$^6$Doc-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. |
| title | RoDLA: Benchmarking the Robustness of Document Layout Analysis Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.14442 |