Table Detection for Visually Rich Document Images
arXiv:2305.19181 · doi:10.1016/j.knosys.2023.111080
Abstract
Table Detection (TD) is a fundamental task to enable visually rich document understanding, which requires the model to extract information without information loss. However, popular Intersection over Union (IoU) based evaluation metrics and IoU-based loss functions for the detection models cannot directly represent the degree of information loss for the prediction results. Therefore, we propose to decouple IoU into a ground truth coverage term and a prediction coverage term, in which the former can be used to measure the information loss of the prediction results. Besides, considering the sparse distribution of tables in document images, we use SparseR-CNN as the base model and further improve the model by using Gaussian Noise Augmented Image Size region proposals and many-to-one label assignments. Results under comprehensive experiments show that the proposed method can consistently outperform state-of-the-art methods with different IoU-based metrics under various datasets and demonstrate that the proposed decoupled IoU loss can enable the model to alleviate information loss.
arXiv commentAccepted by Knowledge-Based Systems
References in corpus (9)
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- Decoupled Weight Decay Regularization
- YOLOX: Exceeding YOLO Series in 2021
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
- UnitBox: An Advanced Object Detection Network
- DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
- You Only Learn One Representation: Unified Network for Multiple Tasks
- 1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
- Revisiting Table Detection Datasets for Visually Rich Documents