Papers › Shape Robust Text Detection with Progressive Scale Expansion Network

Shape Robust Text Detection with Progressive Scale Expansion Network

7 Jun 2018arXiv:1806.02559archive 2025-07-28

Xiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang

The challenges of shape robust text detection lie in two aspects: 1) most existing quadrangular bounding box based detectors are difficult to locate texts with arbitrary shapes, which are hard to be enclosed perfectly in a rectangle; 2) most pixel-wise segmentation-based detectors may not separate the text instances that are very close to each other. To address these problems, we propose a novel Progressive Scale Expansion Network (PSENet), designed as a segmentation-based detector with multiple predictions for each text instance. These predictions correspond to different `kernels' produced by shrinking the original text instance into various scales. Consequently, the final detection can be conducted through our progressive scale expansion algorithm which gradually expands the kernels with minimal scales to the text instances with maximal and complete shapes. Due to the fact that there are large geometrical margins among these minimal kernels, our method is effective to distinguish the adjacent text instances and is robust to arbitrary shapes. The state-of-the-art results on ICDAR 2015 and ICDAR 2017 MLT benchmarks further confirm the great effectiveness of PSENet. Notably, PSENet outperforms the previous best record by absolute 6.37% on the curve text dataset SCUT-CTW1500. Code will be available in https://github.com/whai362/PSENet.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

The archive's official repository (whai362/PSENet) was not harvested; the 24 samples below come from 6 community repositories.

Syntology 24 code samples harvested from 6 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 3 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 24 samples from 6 repositories, 17 ran (15 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 17 samples that ran has no recorded date.

whai362/PSENet officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: not harvested report
A-ZHANG1/PSENet mentioned on GitHubtfApache-2.0Syntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
DePengW/PSENet mentioned on GitHubtfSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
JiaquanYe/TableMASTER-mmocr mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing... (arXiv:2105.01848; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Mael-zys/PSENet mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
SimonWang00/psenet.tf2 mentioned on GitHubtfSyntology: not harvested report
li10141110/PSENet-tf2 mentioned on GitHubtfApache-2.0Syntology: 12 samples, 9 ran (0 instrument-failed) · 3 unverified report
liuheng92/tensorflow_PSENet mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
PaddleEdu/OCR-models-PaddlePaddle paddleApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

24 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 3 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
12ran
7unverified

Licence: 3 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

A-ZHANG1/PSENet community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
conv3x3 in 1,376 papers models/fpn_resnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
resnet18 in 432 papers models/fpn_resnet.py unverified Apache-2.0 (permissive) · 06056d532c6d3ff8 · report
resnet34 in 148 papers models/fpn_resnet.py unverified Apache-2.0 (permissive) · 99c7b9e9359a3aa9 · report
DePengW/PSENet community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32 · arg 3: rank 4, kind float, dtype float32
train_ic15.py ran · violated contract fingerprinted Apache-2.0 (permissive) · ef327e5c61768306 · report fixture: signature input:Tensor/4/float, target:Tensor/4/float, mask:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ohem_batch train_ic15.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 46a8caf20987d0ed · report fixture: signature scores:Tensor/3/float, gt_texts:Tensor/3/float, training_masks:Tensor/3/float · returned Tensor · level recorded 2026-09-22
ohem_single train_ic15.py ran · violated contract fingerprinted Apache-2.0 (permissive) · abc5d78bef2217cc · report fixture: signature score:ndarray/2/float, gt_text:ndarray/2/float, training_mask:ndarray/2/float · returned ndarray · level recorded 2026-09-22
Mael-zys/PSENet community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
extend_3c test_ic15.py ran · violated contract no licence file found · pointer only · 81635961fe760852 · report fixture: signature img:ndarray/2/float · returned ndarray · level recorded 2026-09-22
polygon_from_points test_ic15.py unverified no licence file found · pointer only · 16900bc2a138ef61 · report
li10141110/PSENet-tf2 community (archive-listed) 12 samples, 9 ran (0 instrument-failed) · 3 unverified
conv3x3 in 1,376 papers models/fpn_resnet.py ran Apache-2.0 (permissive) · 7c2df8af7f5531c4 · report fixture: signature out_planes:int/0/int, strides:int/0/int · returned Conv2D · level recorded 2026-09-26
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
train_ctw1500.py ran Apache-2.0 (permissive) · 58bb50d6bc6f6f8f · report fixture: signature input:EagerTensor/2/float, target:EagerTensor/2/float, mask:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
get_img dataset/ctw1500_loader.py ran Apache-2.0 (permissive) · 73f41956a0cd9ce5 · report fixture: signature img_path:str/0/str · returned ndarray · level recorded 2026-09-26
h_sigmoid in 5 papers models/mobilenet_v3_block.py ran fingerprinted Apache-2.0 (permissive) · 9172cf3729410434 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
h_swish models/mobilenet_v3_block.py ran fingerprinted Apache-2.0 (permissive) · 49d4334289825356 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
ohem_batch train_ctw1500.py ran Apache-2.0 (permissive) · 61c1a6deb519c1b4 · report fixture: signature scores:EagerTensor/3/float, gt_texts:EagerTensor/3/float, training_masks:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-26
pse pypse.py ran Apache-2.0 (permissive) · 2473fba7e2d2183a · report fixture: signature kernals:list/1/ndarray, min_area:int/0/int · returned ndarray · level recorded 2026-09-26
random_horizontal_flip dataset/ctw1500_loader.py ran fingerprinted Apache-2.0 (permissive) · eab615268dca3a00 · report fixture: signature imgs:list/1/ndarray · returned list · level recorded 2026-09-26
scale in 38 papers dataset/ctw1500_test_loader.py ran fingerprinted Apache-2.0 (permissive) · aff0e449324bf982 · report fixture: signature img:ndarray/3/int, long_size:int/0/int · returned ndarray · level recorded 2026-09-26
MobileNetv2 MobileNetV2/mobilenet_v2.py unverified Apache-2.0 (permissive) · 4a0dff2bd619eb72 · report
mobilenetv2 in 7 papers models/fpn_resnet.py unverified Apache-2.0 (permissive) · 54822bc5ab637521 · report
relu6 in 14 papers MobileNetV2/mobilenet_v2.py unverified Apache-2.0 (permissive) · d51adc9e749c6f92 · report
liuheng92/tensorflow_PSENet community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
load_annoataion utils/data_provider/data_provider.py ran fingerprinted MIT (permissive) · f539910065f78fcb · report fixture: signature p:str/0/str · returned tuple · level recorded 2026-09-26
mean_image_subtraction nets/model.py ran MIT (permissive) · 9bfc6628f89669e9 · report fixture: signature images:EagerTensor/4/float, means:list/1/float · returned EagerTensor · level recorded 2026-09-26
unpool nets/model.py unverified MIT (permissive) · b6b0d40667b0f177 · report
PaddleEdu/OCR-models-PaddlePaddle community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
pse PSENet/models/pypse.py ran Apache-2.0 (permissive) · 960fcfbe3f86f157 · report fixture: signature kernals:list/1/ndarray, min_area:int/0/int · returned ndarray · level recorded 2026-09-26

Tasks

Curved Text DetectionScene Text DetectionText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2015 PSENet-1s F-Measure 87.1 #17 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PSENet-1s Precision 88.7 #17 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PSENet-1s Recall 85.5 #17 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT PSENet-1s F-Measure 72.45% #12 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT PSENet-1s Precision 77.01 #12 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT PSENet-1s Recall 68.4 #12 of 14 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 PSENet-1s F-Measure 81.17 #15 of 17 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 PSENet-1s Precision 82.5 #15 of 17 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 PSENet-1s Recall 79.89 #15 of 17 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