</> Code with Papers by Syntology

Papers › Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion

Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion

21 Feb 2022arXiv:2202.10304archive 2025-07-28

Minghui Liao, Zhisheng Zou, Zhaoyi Wan, Cong Yao, Xiang Bai

Recently, segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field, because of their superiority in detecting the text instances of arbitrary shapes and extreme aspect ratios, profiting from the pixel-level descriptions. However, the vast majority of the existing segmentation-based approaches are limited to their complex post-processing algorithms and the scale robustness of their segmentation models, where the post-processing algorithms are not only isolated to the model optimization but also time-consuming and the scale robustness is usually strengthened by fusing multi-scale feature maps directly. In this paper, we propose a Differentiable Binarization (DB) module that integrates the binarization process, one of the most important steps in the post-processing procedure, into a segmentation network. Optimized along with the proposed DB module, the segmentation network can produce more accurate results, which enhances the accuracy of text detection with a simple pipeline. Furthermore, an efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively. By incorporating the proposed DB and ASF with the segmentation network, our proposed scene text detector consistently achieves state-of-the-art results, in terms of both detection accuracy and speed, on five standard benchmarks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

MhLiao/DB officialmentioned on GitHubpytorch report
JaidedAI/EasyOCR mentioned on GitHubpytorch report
open-mmlab/mmocr mentioned on GitHubpytorchApache-2.0 report
PaddlePaddle/PaddleOCR paddleApache-2.0 report
mindspore-lab/mindocr mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

BinarizationModel OptimizationScene Text DetectionSegmentationText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-50) (1152) F-Measure 87.3 #14 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-50) (1152) FPS 10 #14 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-50) (1152) Precision 90.9 #14 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-50) (1152) Recall 83.9 #14 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-18) (736) F-Measure 83.1 #30 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-18) (736) FPS 44 #30 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-18) (736) Precision 90.1 #30 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DBNet++ (ResNet-18) (736) Recall 77.2 #30 of 43 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-50) (736) F-Measure 87.2 #3 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-50) (736) FPS 29 #3 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-50) (736) Precision 91.5 #3 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-50) (736) Recall 83.3 #3 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (736) F-Measure 85.1 #5 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (736) FPS 55 #5 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (736) Precision 87.9 #5 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (736) Recall 82.5 #5 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (512) F-Measure 82.6 #11 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (512) FPS 80 #11 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (512) Precision 89.7 #11 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DBNet++ (ResNet-18) (512) Recall 76.5 #11 of 18 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-50) (800) F-Measure 86% #9 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-50) (800) FPS 28 #9 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-50) (800) Precision 88.9 #9 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-50) (800) Recall 83.2 #9 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-18) (800) F-Measure 83.3% #18 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-18) (800) FPS 48 #18 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-18) (800) Precision 87.4 #18 of 27 Archive leaderboard report
Scene Text Detection Total-Text DBNet++ (ResNet-18) (800) Recall 79.6 #18 of 27 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.

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