Papers › Real-time Scene Text Detection with Differentiable Binarization

Real-time Scene Text Detection with Differentiable Binarization

20 Nov 2019arXiv:1911.08947archive 2025-07-28

Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, Xiang Bai

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

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1911.08947")

Code

Syntology Ran 3 of 25 code samples harvested from 6 repositories linked to this paper; 22 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 25 samples from 6 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

15 repositories listed; official and paper-mentioned ones first.

MhLiao/DB officialmentioned in papermentioned on GitHubpytorch report
18520339/dbnet-tf2 mentioned on GitHubtfMIT report
2023-MindSpore-1/ms-code-43 mentioned on GitHubmindspore report
Mushroomcat9998/DBNet mentioned on GitHubpytorchApache-2.0 report
PaddlePaddle/PaddleOCR mentioned on GitHubpaddleApache-2.0 report
SURFZJY/Real-time-Text-Detection mentioned on GitHubpytorchApache-2.0 report
WenmuZhou/DBNet.pytorch mentioned on GitHubpytorchApache-2.0 report
WenmuZhou/PytorchOCR mentioned on GitHubpytorch report
huyhoang17/DB_text_minimal mentioned on GitHubpytorchMIT report
jakeywu/ocr_torch mentioned on GitHubpytorch report
mindee/doctr mentioned on GitHubpytorchApache-2.0 report
yanan0122/dbnet-and-dbnet_pp-by-mind-spore mentioned on GitHubmindspore report
mindspore-lab/mindocr mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
open-mmlab/mmocr pytorchApache-2.0 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

25 samples harvested; 3 ran; 0 honoured the contract we drafted; 22 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
22unverified

Licence: 0 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv1x1 SURFZJY/Real-time-Text-Detection/models/modules/resnet.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report
conv3x3 SURFZJY/Real-time-Text-Detection/models/modules/resnet.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 160bb14bd76201b4 · report
conv3x3 WenmuZhou/DBNet.pytorch/models/backbone/resnet.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · fac5364e2f53c6db · report
cal_text_score huyhoang17/DB_text_minimal/src/text_metrics.py community (archive-listed) unverified MIT (permissive) · 0b16bed946565da6 · report
check_and_validate_polys SURFZJY/Real-time-Text-Detection/data_loader/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 07471b3162a18b9d · report
compute_distance huyhoang17/DB_text_minimal/src/db_transforms.py community (archive-listed) unverified MIT (permissive) · 0362f3cc6b5edc59 · report
crop_patch 18520339/dbnet-tf2/tfdbnet/utils.py community (archive-listed) unverified MIT (permissive) · 380431820253ae48 · report
dcn_conv3x3 SURFZJY/Real-time-Text-Detection/models/modules/resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · f9244a258a55a5ab · report
deformable_resnet18 WenmuZhou/DBNet.pytorch/models/backbone/resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · ae0dd302eac3e5eb · report
get_images SURFZJY/Real-time-Text-Detection/genText.py community (archive-listed) unverified Apache-2.0 (permissive) · b1827bd3314d5a57 · report
get_max_width_length_ratio mindee/doctr/doctr/models/_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 14c65cfb11d94847 · report
get_txts SURFZJY/Real-time-Text-Detection/genText.py community (archive-listed) unverified Apache-2.0 (permissive) · acbee53c5f8e1a9a · report
quadratic SURFZJY/Real-time-Text-Detection/data_loader/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · a133283a2aa3440f · report
rectify_crops mindee/doctr/doctr/models/_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 0ef99817b8bb3cdb · report
resize_image Mushroomcat9998/DBNet/data_loader/modules/augment.py community (archive-listed) unverified Apache-2.0 (permissive) · 74c3e5afa7495d81 · report
resize_image_short_side 18520339/dbnet-tf2/tfdbnet/utils.py community (archive-listed) unverified MIT (permissive) · a5ebf7edacfab1eb · report
resnet18 WenmuZhou/DBNet.pytorch/models/backbone/resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · 7bee880a6603be77 · report
shrink_polygon_py Mushroomcat9998/DBNet/data_loader/modules/make_shrink_map.py community (archive-listed) unverified Apache-2.0 (permissive) · a48b1586c42ff5fe · report
shrink_polygon_pyclipper Mushroomcat9998/DBNet/data_loader/modules/make_shrink_map.py community (archive-listed) unverified Apache-2.0 (permissive) · e5fc5488f52a4d68 · report
split_regions huyhoang17/DB_text_minimal/src/db_transforms.py community (archive-listed) unverified MIT (permissive) · af7b1b462f45fefc · report
step_function huyhoang17/DB_text_minimal/src/losses.py community (archive-listed) unverified MIT (permissive) · 06d815aba9fc17d6 · report
test_preprocess huyhoang17/DB_text_minimal/src/db_handler.py community (archive-listed) unverified MIT (permissive) · bcb66632e553eda2 · report
test_resize huyhoang17/DB_text_minimal/src/db_handler.py community (archive-listed) unverified MIT (permissive) · 80b87673405e6943 · report
to_list_tuples huyhoang17/DB_text_minimal/src/make_eval.py community (archive-listed) unverified MIT (permissive) · a8adaa21874014ed · report
unshrink_offset SURFZJY/Real-time-Text-Detection/data_loader/data_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · d1012dc3a8f720ea · report

Tasks

BinarizationOptical Character Recognition (OCR)Scene Text DetectionSegmentationText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2015 DB-ResNet-50 (1152) F-Measure 87.3 #13 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DB-ResNet-50 (1152) Precision 91.8 #13 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 DB-ResNet-50 (1152) Recall 83.2 #13 of 43 Archive leaderboard report
Scene Text Detection MSRA-TD500 DB-ResNet-50 (736) F-Measure 84.9 #6 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DB-ResNet-50 (736) Precision 91.5 #6 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 DB-ResNet-50 (736) Recall 79.2 #6 of 18 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 DB-ResNet50 (1024) F-Measure 83.4 #10 of 17 Archive leaderboard report
Scene Text Detection Total-Text DB-ResNet-50 (800) F-Measure 84.7% #15 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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