mlsanityData to 14 Oct 2026

Real-time Scene Text Detection with Differentiable Binarization

arXiv 1911.08947 ↗First posted 20 Nov 2019cs.CVcited by 214

Not on the map. Why?

Abstract (arXiv)

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text. In this paper, we propose a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network. Optimized along with a DB module, a segmentation network can adaptively set the thresholds for binarization, which not only simplifies the post-processing but also enhances the performance of text detection. Based on a simple segmentation network, we validate the performance improvements of DB on five benchmark datasets, which consistently achieves state-of-the-art results, in terms of both detection accuracy and speed. In particular, with a light-weight backbone, the performance improvements by DB are significant so that we can look for an ideal tradeoff between detection accuracy and efficiency. Specifically, with a backbone of ResNet-18, our detector achieves an F-measure of 82.8, running at 62 FPS, on the MSRA-TD500 dataset. Code is available at: https://github.com/MhLiao/DB

Key facts. Cited by 214 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 34; 2022: 40; 2023: 41; 2024: 45; 2025: 33; 2026: 21.

214 papers.

Sort:

By area:

  1. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 279
  2. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  3. 2023TextDiffuser-2: Unleashing the Power of Language Models for Text Renderingcited by 140
  4. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 131
  5. 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
  6. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 106
  7. 2023DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understandingcited by 106
  8. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  9. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  10. 2021Fourier Contour Embedding for Arbitrary-Shaped Text Detectioncited by 80
  11. 2024TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergycited by 71
  12. 2024AppAgent v2: Advanced Agent for Flexible Mobile Interactionscited by 68
38 more
  1. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  2. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  3. 2022DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformercited by 50
  4. 2021Adaptive Boundary Proposal Network for Arbitrary Shape Text Detectioncited by 47
  5. 2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
  6. 2023Turning a CLIP Model into a Scene Text Detectorcited by 44
  7. 2021MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understandingcited by 40
  8. 2023GeoLayoutLM: Geometric Pre-training for Visual Information Extractioncited by 40
  9. 2021PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR Systemcited by 39
  10. 2022MaskOCR: Text Recognition with Masked Encoder-Decoder Pretrainingcited by 34
  11. 2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34
  12. 2024SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimapcited by 34
  13. 2021MOST: A Multi-Oriented Scene Text Detector with Localization Refinementcited by 33
  14. 2022Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learningcited by 33
  15. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  16. 2023ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformercited by 29
  17. 2022Arbitrary Shape Text Detection via Boundary Transformercited by 28
  18. 2022Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spottingcited by 27
  19. 2023Towards Unified Scene Text Spotting based on Sequence Generationcited by 27
  20. 2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
  21. 2021A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformercited by 26
  22. 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generationcited by 25
  23. 2021De-rendering Stylized Textscited by 24
  24. 2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
  25. 2023ICDAR 2023 Competition on Hierarchical Text Detection and Recognitioncited by 23
  26. 2021Stroke-Based Scene Text Erasing Using Synthetic Data for Trainingcited by 20
  27. 2023ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Imagescited by 20
  28. 2023Toward Real Text Manipulation Detection: New Dataset and New Solutioncited by 20
  29. 2023SOOD: Towards Semi-Supervised Oriented Object Detectioncited by 19
  30. 2023DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documentscited by 19
  31. 2022Vision-Language Pre-Training for Boosting Scene Text Detectorscited by 18
  32. 2022Kernel Proposal Network for Arbitrary Shape Text Detectioncited by 17
  33. 2021Industrial Scene Text Detection with Refined Feature-attentive Networkcited by 16
  34. 2023Deep Unrestricted Document Image Rectificationcited by 16
  35. 2024First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blendingcited by 16
  36. 2021Scene Text Retrieval via Joint Text Detection and Similarity Learningcited by 15
  37. 2022Arbitrary Shape Text Detection via Segmentation with Probability Mapscited by 15
  38. 2021I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detectioncited by 14

50 most cited of 214 All 214 (JSON)