Papers › BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

2 Aug 2018ECCV 2018 9arXiv:1808.00897archive 2025-07-28

Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048x1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.

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 18 code samples harvested from 7 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 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): 18 samples from 7 repositories, 14 ran (9 with no instrument failure; 5 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 6 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 14 samples that ran has no recorded date.

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

AmrElsersy/PointPainting mentioned on GitHubpytorchSyntology: not harvested report
Blaizzy/BiSeNet-Implementation mentioned on GitHubtfSyntology: not harvested report
CodePlay2016/BiSENet-TF mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
CoinCheung/BiSeNet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
GuangyanZhang/SCNN-Deeplabv3-bisenet-icnet mentioned on GitHubpaddleSyntology: not harvested report
SharifElfouly/easy-model-zoo mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientDet: Scalable and Efficient Object Detection (arXiv:1911.09070; that paper's own run record: 55 ran (of which 1 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
Shuai-Xie/BiSeNet-CCP mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
akinoriosamura/TorchSeg-mirror mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
hm7455/Anti-collision_Semantic-segmentation_ mentioned on GitHubtfSyntology: not harvested report
kirilcvetkov92/Semantic-Segmentation mentioned on GitHubSyntology: not harvested report
kritiksoman/GIMP-ML mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation (arXiv:2011.06294; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified) and Vision Transformers for Dense Prediction (arXiv:2103.13413; that paper's own run record: 65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
ooooverflow/BiSeNet mentioned on GitHubpytorchSyntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
pdoublerainbow/bisenet-tensorflow mentioned on GitHubtfMITSyntology: not harvested report
renhaa/semantic-diffusion mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models (arXiv:2303.11073; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
yakhyo/face-parsing mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ycszen/TorchSeg mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
zh320/realtime-semantic-segmentation-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CGNet: A Light-weight Context Guided Network for Semantic Segmentation (arXiv:1811.08201; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network (arXiv:1811.11431; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified), Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Asthestarsfalll/BiSeNet-MegEngine pytorchSyntology: not harvested report
PaddlePaddle/PaddleSeg paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow (arXiv:2109.09406; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
justld/BisNetV1_paddle paddleApache-2.0Syntology: 5 samples, 5 ran (2 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

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 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.

4ran · our draft was wrong
1ran; the contract check could not run
9ran
4unverified

Licence: 3 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 7 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.

CodePlay2016/BiSENet-TF community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
expand_input_by_factor frontends/conv_blocks.py ran MIT (permissive) · 2bd76ec2dd72540c · report fixture: signature n:int/0/int, divisible_by:int/0/int · returned function · level recorded 2026-09-25
one_hot_it Dataset/dataset.py ran MIT (permissive) · dd997f5e1e079e4c · report fixture: signature label:EagerTensor/3/int, label_values:list/1/EagerTensor · returned SymbolicTensor · level recorded 2026-09-26
relu6 in 14 papers models/bisenet.py ran MIT (permissive) · fcc1c65dadc2827f · report fixture: signature x:EagerTensor/2/float, name:str/0/str · returned EagerTensor · level recorded 2026-09-26
wrapped_partial in 12 papers frontends/mobilenet_v2.py ran MIT (permissive) · b6e06004f7efe660 · report fixture: signature func:callable/0/?, args:tuple/1/int, kwargs:dict/0/? · returned partial · level recorded 2026-09-24
Upsampling models/bisenet.py unverified MIT (permissive) · 8cce015ae2806199 · report
CoinCheung/BiSeNet community (archive-listed) 1 sample, 0 ran · 1 unverified
set_model_dist tools/train_amp.py unverified MIT (permissive) · 5c1d86977d83a6be · report
Shuai-Xie/BiSeNet-CCP community (archive-listed) 1 sample, 0 ran · 1 unverified
label_color2value instance_seg.py unverified no licence file found · pointer only · ffc753a7daae83ae · report
akinoriosamura/TorchSeg-mirror community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
compute_score in 49 papers furnace/seg_opr/metric.py ran MIT (permissive) · 3e98ad928a86de29 · report fixture: signature hist:ndarray/2/float, correct:int/0/int, labeled:int/0/int · returned tuple · level recorded 2026-09-25
conv3x3 in 1,376 papers furnace/base_model/resnet.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
hist_info furnace/seg_opr/metric.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted MIT (permissive) here; the stored copy is pointer only · 9e85fa995eda358a · report fixture: signature n_cl:int/0/int, pred:ndarray/1/int, gt:ndarray/1/int · returned tuple · level recorded 2026-09-22
meanIoU furnace/seg_opr/metric.py ran fingerprinted MIT (permissive) · be62e3869efd8038 · report fixture: signature area_intersection:ndarray/2/float, area_union:ndarray/2/float · returned tuple · level recorded 2026-09-25
yakhyo/face-parsing community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_files_to_process inference.py ran · our draft was wrong MIT (permissive) · 5f61c6982f852ba1 · report fixture: signature input_path:str/0/str · returned list · level recorded 2026-09-22
ycszen/TorchSeg community (archive-listed) 1 sample, 0 ran · 1 unverified
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
furnace/seg_opr/seg_oprs.py unverified MIT (permissive) · ce0cd041399bf007 · report
justld/BisNetV1_paddle community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
flip_combination in 8 papers paddleseg/core/infer.py ran Apache-2.0 (permissive) · 95bccf5957a196e4 · report fixture: signature flip_horizontal:bool/0/bool, flip_vertical:bool/0/bool · returned list · level recorded 2026-09-24
get_reverse_list in 8 papers paddleseg/core/infer.py ran Apache-2.0 (permissive) · a5dbdd4f2d59692e · report fixture: signature ori_shape:list/1/int, transforms:list/1/Resize · returned list · level recorded 2026-09-26
get_test_config in 9 papers val.py ran · our draft was wrong Apache-2.0 (permissive) · 20eb3e6b0aba73e4 · report fixture: signature cfg:SimpleConfig/0/?, args:SimpleArgs/0/? · returned dict · level recorded 2026-09-22
get_test_config in 9 papers predict.py ran Apache-2.0 (permissive) · 0b3ec74bd2e5ed5d · report fixture: signature cfg:MockConfig/0/?, args:MockArgs/0/? · returned dict · level recorded 2026-09-26
partition_list in 10 papers paddleseg/core/predict.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report fixture: signature arr:list/1/int, m:int/0/int · returned list · level recorded 2026-09-22

Tasks

Dichotomous Image SegmentationReal-Time Semantic SegmentationSegmentationSemantic SegmentationThermal Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dichotomous Image Segmentation DIS-TE1 BSV1 E-measure 0.741 #22 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BSV1 HCE 288 #22 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BSV1 MAE 0.108 #22 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BSV1 S-Measure 0.695 #22 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BSV1 max F-Measure 0.595 #22 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BSV1 weighted F-measure 0.474 #22 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BSV1 E-measure 0.781 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BSV1 HCE 621 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BSV1 MAE 0.111 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BSV1 S-Measure 0.740 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BSV1 max F-Measure 0.680 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BSV1 weighted F-measure 0.564 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BSV1 E-measure 0.801 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BSV1 HCE 1146 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BSV1 MAE 0.109 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BSV1 S-Measure 0.757 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BSV1 max F-Measure 0.710 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BSV1 weighted F-measure 0.595 #21 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BSV1 E-measure 0.788 #20 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BSV1 HCE 3999 #20 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BSV1 MAE 0.114 #20 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BSV1 S-Measure 0.755 #20 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BSV1 max F-Measure 0.710 #20 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BSV1 weighted F-measure 0.598 #20 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BSV1 E-measure 0.767 #22 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BSV1 HCE 1660 #22 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BSV1 MAE 0.116 #22 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BSV1 S-Measure 0.728 #22 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BSV1 max F-Measure 0.662 #22 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BSV1 weighted F-measure 0.548 #22 of 24 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet mIoU 68.7% #22 of 29 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet(ResNet-18) Frame (fps) 65.5 #18 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet(ResNet-18) Time (ms) 15.2 #18 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet(ResNet-18) mIoU 74.7% #18 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet Frame (fps) 65.5 #19 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet mIoU 74.7% #19 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet(Xception39) Frame (fps) 105.8 #32 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet(Xception39) Time (ms) 9.5 #32 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet(Xception39) mIoU 68.4% #32 of 39 Archive leaderboard report
Semantic Segmentation BDD100K val BiSeNet-V1(ResNet-18) mIoU 53.8(45.1fps) #12 of 24 Archive leaderboard report
Semantic Segmentation CamVid BiSeNet Mean IoU 68.7% #11 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test BiSeNet (ResNet-101) Mean IoU (class) 78.9% #58 of 105 Archive leaderboard report
Semantic Segmentation SkyScapes-Dense BiSeNet (ResNet-50) Mean IoU 30.82 #4 of 7 Archive leaderboard report
Semantic Segmentation Trans10K BiSeNet GFLOPs 19.91 #12 of 15 Archive leaderboard report
Semantic Segmentation Trans10K BiSeNet mIoU 58.40% #12 of 15 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 ConnectionSPEED

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