Papers › PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers

PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers

4 Jun 2022CVPR 2023 1arXiv:2206.02066archive 2025-07-28

Jiacong Xu, Zixiang Xiong, Shankar P. Bhattacharyya

Two-branch network architecture has shown its efficiency and effectiveness in real-time semantic segmentation tasks. However, direct fusion of high-resolution details and low-frequency context has the drawback of detailed features being easily overwhelmed by surrounding contextual information. This overshoot phenomenon limits the improvement of the segmentation accuracy of existing two-branch models. In this paper, we make a connection between Convolutional Neural Networks (CNN) and Proportional-Integral-Derivative (PID) controllers and reveal that a two-branch network is equivalent to a Proportional-Integral (PI) controller, which inherently suffers from similar overshoot issues. To alleviate this problem, we propose a novel three-branch network architecture: PIDNet, which contains three branches to parse detailed, context and boundary information, respectively, and employs boundary attention to guide the fusion of detailed and context branches. Our family of PIDNets achieve the best trade-off between inference speed and accuracy and their accuracy surpasses all the existing models with similar inference speed on the Cityscapes and CamVid datasets. Specifically, PIDNet-S achieves 78.6% mIOU with inference speed of 93.2 FPS on Cityscapes and 80.1% mIOU with speed of 153.7 FPS on CamVid.

PaperPDFConference PDFCodeCode 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

Syntology 19 code samples harvested from 5 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 18 samples from 4 repositories, 8 ran (7 with no instrument failure; 1 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.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 9 samples that ran has no recorded date.

XuJiacong/PIDNet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
HengWeiBin/Oil-Polution-Dataset-with-PIDNet mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
Mahmood-Hussain/PIDNetTensorflow mentioned on GitHubtfSyntology: not harvested report
enot-autodl/lpcv-2023 mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
hamidriasat/PIDNet mentioned on GitHubtfMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
Darth-Kronos/PIDNet_TensorRT pytorchMITSyntology: 8 samples, 2 ran (1 instrument-failed) · 6 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.

Code Syntology ran Syntology

19 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 10 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.

1ran · our draft was wrong
8ran
10unverified

Licence: 2 of the 19 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 5 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.

XuJiacong/PIDNet official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
weighted_bce utils/criterion.py ran fingerprinted MIT (permissive) · f0b6abd190ebe3a4 · report fixture: signature bd_pre:Tensor/4/float, target:Tensor/4/float · returned Tensor · level recorded 2026-09-24
HengWeiBin/Oil-Polution-Dataset-with-PIDNet community (archive-listed) 2 samples, 0 ran · 2 unverified
get_pred_model models/pidnet.py unverified MIT (permissive) · 9d7c08e2a8e12ed1 · report
get_seg_model in 8 papers models/pidnet.py unverified MIT (permissive) · 178ee10b1aeec3d6 · report
enot-autodl/lpcv-2023 community (archive-listed) 1 sample, 0 ran · 1 unverified
get_seg_model in 8 papers training/models/pidnet.py unverified no licence file found · pointer only · 5089f1565526fc75 · report
hamidriasat/PIDNet community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
DAPPPM model_utils.py ran fingerprinted MIT (permissive) · 4acac2201e2de928 · report fixture: signature x_in:EagerTensor/4/float, branch_planes:int/0/int, outplanes:int/0/int · returned EagerTensor · level recorded 2026-09-24
basic_block in 6 papers resnet.py ran MIT (permissive) · 92809dd5a449eb93 · report fixture: signature x_in:EagerTensor/4/float, planes:int/0/int, stride:int/0/int, downsample:EagerTensor/4/float, no_relu:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
bottleneck_block in 6 papers resnet.py ran MIT (permissive) · b55dd2da33385622 · report fixture: signature x_in:EagerTensor/4/float, planes:int/0/int, stride:int/0/int, downsample:EagerTensor/4/float, no_relu:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
conv3x3 in 1,376 papers resnet.py ran MIT (permissive) · fa1dd696ceb3bffe · report fixture: signature out_planes:int/0/int, stride:int/0/int · returned Conv2D · level recorded 2026-09-24
make_layer in 76 papers pidnet.py ran MIT (permissive) · ce795ae2777c861e · report fixture: signature x_in:KerasTensor/4/float, block:callable/0/?, inplanes:int/0/int, planes:int/0/int, blocks_num:int/0/int, stride:int/0/int, expansion:int/0/int · returned KerasTensor · level recorded 2026-09-24
segmentation_head model_utils.py ran MIT (permissive) · 6907f597f9f56894 · report fixture: signature x_in:EagerTensor/4/float, interplanes:int/0/int, outplanes:int/0/int, scale_factor:int/0/int · returned EagerTensor · level recorded 2026-09-24
PAPPM model_utils.py unverified MIT (permissive) · 905b5242a35e7ed7 · report
Darth-Kronos/PIDNet_TensorRT community (archive-listed) 8 samples, 2 ran (1 instrument-failed) · 6 unverified
conv3x3 in 1,376 papers models/others/bisenet_adb_bag.py ran · our draft was wrong MIT (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
create_layer_basic in 19 papers models/others/resnet.py ran MIT (permissive) · 92a9102d957a0f37 · report fixture: signature in_chan:int/0/int, out_chan:int/0/int, bnum:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-24
Bisenet_Adb_Bag models/others/bisenet_adb_bag.py unverified MIT (permissive) · acf0e83d3b5b6f01 · report
DualResNet_imagenet models/others/ddrnet_23_adb_bag.py unverified MIT (permissive) · f870abc3d49177be · report
get_pred_model models/pidnet.py unverified MIT (permissive) · 603274398f6b4944 · report
get_seg_model in 8 papers models/pidnet.py unverified MIT (permissive) · fb6020f30ebc7f12 · report
get_seg_model in 8 papers models/others/bisenet_adb_bag.py unverified MIT (permissive) · 77136b5a94e0104e · report
get_seg_model in 8 papers models/others/ddrnet_23_adb_bag.py unverified MIT (permissive) · a4a5b2b55ece38ff · report

Tasks

Real-Time Semantic SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation CamVid PIDNet-M (Cityscapes-Pretrained) Frame (fps) 85.6(3090) #1 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PIDNet-M (Cityscapes-Pretrained) Time (ms) 11.7 #1 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PIDNet-M (Cityscapes-Pretrained) mIoU 82.0 #1 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PIDNet-S (Cityscapes-Pretrained) Frame (fps) 153.7(3090) #6 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PIDNet-S (Cityscapes-Pretrained) Time (ms) 6.5 #6 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PIDNet-S (Cityscapes-Pretrained) mIoU 80.1 #6 of 29 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-L Frame (fps) 31.1(3090) #1 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-L Time (ms) 32.2 #1 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-L mIoU 80.6% #1 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-M Frame (fps) 42.2(3090) #3 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-M Time (ms) 23.7 #3 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-M mIoU 79.8% #3 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-S Frame (fps) 93.2(3090) #4 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-S Time (ms) 10.7 #4 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test PIDNet-S mIoU 78.6% #4 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-L Frame (fps) 31.1(3090) #1 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-L Time (ms) 32.2 #1 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-L mIoU 80.9% #1 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-M Frame (fps) 42.2(3090) #3 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-M Time (ms) 23.7 #3 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-M mIoU 79.9% #3 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-S Frame (fps) 93.2(3090) #7 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-S Time (ms) 10.7 #7 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val PIDNet-S mIoU 78.8% #7 of 24 Archive leaderboard report
Semantic Segmentation CamVid PIDNet-Wider Mean IoU 82.0% #5 of 21 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

SPEED

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