mlsanityData to 7 Oct 2026

Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer

arXiv 2305.02769 ↗First posted 4 May 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Table detection is the task of classifying and localizing table objects within document images. With the recent development in deep learning methods, we observe remarkable success in table detection. However, a significant amount of labeled data is required to train these models effectively. Many semi-supervised approaches are introduced to mitigate the need for a substantial amount of label data. These approaches use CNN-based detectors that rely on anchor proposals and post-processing stages such as NMS. To tackle these limitations, this paper presents a novel end-to-end semi-supervised table detection method that employs the deformable transformer for detecting table objects. We evaluate our semi-supervised method on PubLayNet, DocBank, ICADR-19 and TableBank datasets, and it achieves superior performance compared to previous methods. It outperforms the fully supervised method (Deformable transformer) by +3.4 points on 10% labels of TableBank-both dataset and the previous CNN-based semi-supervised approach (Soft Teacher) by +1.8 points on 10% labels of PubLayNet dataset. We hope this work opens new possibilities towards semi-supervised and unsupervised table detection methods.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 43 of its 95 references that are in the map. First posted on arXiv 4 May 2023.

Builds on

43 of 95 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2015Fast R-CNNcited by 2,930
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  11. 2017Deformable Convolutional Networkscited by 1,481
  12. 2016YOLO9000: Better, Faster, Strongercited by 1,429
31 more
  1. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  2. 2018Image Transformercited by 770
  3. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  4. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  5. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 420
  6. 2019Attention Augmented Convolutional Networkscited by 363
  7. 2020Rethinking Pre-training and Self-trainingcited by 352
  8. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  9. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  10. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  11. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  12. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  13. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 152
  14. 2020Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Contextcited by 146
  15. 2017Data Distillation: Towards Omni-Supervised Learningcited by 126
  16. 2021PubTables-1M: Towards comprehensive table extraction from unstructured documentscited by 122
  17. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  18. 2020CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documentscited by 98
  19. 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
  20. 2018M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Networkcited by 76
  21. 2020TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Imagescited by 69
  22. 2020Proposal Learning for Semi-Supervised Object Detectioncited by 55
  23. 2019CBNet: A Novel Composite Backbone Network Architecture for Object Detectioncited by 44
  24. 2021VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relationscited by 40
  25. 2020Improving Object Detection with Selective Self-supervised Self-trainingcited by 35
  26. 2018Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detectioncited by 32
  27. 2020CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Imagescited by 22
  28. 2020Graphical Object Detection in Document Imagescited by 19
  29. 2020IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documentscited by 16
  30. 2018A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documentscited by 15
  31. 2021Guided Table Structure Recognition through Anchor Optimizationcited by 15

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6.

7 papers.

  1. 2023Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Imagescited by 7
  2. 2024A Hybrid Approach for Document Layout Analysis in Document imagescited by 6
  3. 2024Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformercited by 5
  4. 2024End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documentscited by 4
  5. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  6. 2024UnSupDLA: Towards Unsupervised Document Layout Analysiscited by 2
  7. 2024Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verificationcited by 1