Papers › Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in...

Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images

23 Jun 2023arXiv:2306.13526archive 2025-07-28

Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal

This paper takes an important step in bridging the performance gap between DETR and R-CNN for graphical object detection. Existing graphical object detection approaches have enjoyed recent enhancements in CNN-based object detection methods, achieving remarkable progress. Recently, Transformer-based detectors have considerably boosted the generic object detection performance, eliminating the need for hand-crafted features or post-processing steps such as Non-Maximum Suppression (NMS) using object queries. However, the effectiveness of such enhanced transformer-based detection algorithms has yet to be verified for the problem of graphical object detection. Essentially, inspired by the latest advancements in the DETR, we employ the existing detection transformer with few modifications for graphical object detection. We modify object queries in different ways, using points, anchor boxes and adding positive and negative noise to the anchors to boost performance. These modifications allow for better handling of objects with varying sizes and aspect ratios, more robustness to small variations in object positions and sizes, and improved image discrimination between objects and non-objects. We evaluate our approach on the four graphical datasets: PubTables, TableBank, NTable and PubLaynet. Upon integrating query modifications in the DETR, we outperform prior works and achieve new state-of-the-art results with the mAP of 96.9\%, 95.7\% and 99.3\% on TableBank, PubLaynet, PubTables, respectively. The results from extensive ablations show that transformer-based methods are more effective for document analysis analogous to other applications. We hope this study draws more attention to the research of using detection transformers in document image analysis.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document Layout Analysis Object Object Detection object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Document Layout Analysis	PubLayNet val	DETR	Figure	0.975	#4 of 15	Archive leaderboard	report
Document Layout Analysis	PubLayNet val	DETR	List	0.964	#4 of 15	Archive leaderboard	report
Document Layout Analysis	PubLayNet val	DETR	Overall	0.957	#4 of 15	Archive leaderboard	report
Document Layout Analysis	PubLayNet val	DETR	Table	0.981	#4 of 15	Archive leaderboard	report
Document Layout Analysis	PubLayNet val	DETR	Text	0.947	#4 of 15	Archive leaderboard	report
Document Layout Analysis	PubLayNet val	DETR	Title	0.918	#4 of 15	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Detr Dropout Feedforward Network Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections