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 View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

MhLiao/DB officialmentioned on GitHubpytorchSyntology: not harvested report
JaidedAI/EasyOCR mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmocr mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
PaddlePaddle/PaddleOCR paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to... (arXiv:2508.19944; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
mindspore-lab/mindocr mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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