Papers › BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation

5 Apr 2020arXiv:2004.02147archive 2025-07-28

Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, Nong Sang

The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable accuracy decrease. We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation. To this end, we propose an efficient and effective architecture with a good trade-off between speed and accuracy, termed Bilateral Segmentation Network (BiSeNet V2). This architecture involves: (i) a Detail Branch, with wide channels and shallow layers to capture low-level details and generate high-resolution feature representation; (ii) a Semantic Branch, with narrow channels and deep layers to obtain high-level semantic context. The Semantic Branch is lightweight due to reducing the channel capacity and a fast-downsampling strategy. Furthermore, we design a Guided Aggregation Layer to enhance mutual connections and fuse both types of feature representation. Besides, a booster training strategy is designed to improve the segmentation performance without any extra inference cost. Extensive quantitative and qualitative evaluations demonstrate that the proposed architecture performs favourably against a few state-of-the-art real-time semantic segmentation approaches. Specifically, for a 2,048x1,024 input, we achieve 72.6% Mean IoU on the Cityscapes test set with a speed of 156 FPS on one NVIDIA GeForce GTX 1080 Ti card, which is significantly faster than existing methods, yet we achieve better segmentation accuracy.

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

Syntology 10 code samples: 9 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 10: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 3 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 4 repositories, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

CoinCheung/BiSeNet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
MaybeShewill-CV/bisenetv2-tensorflow mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
hamidriasat/BiSeNetV2 mentioned on GitHubtfMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
ycszen/BiSeNet mentioned on GitHubSyntology: not harvested 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
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

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

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 3 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

2ran · honoured contract
3ran · violated contract
1ran; the contract check could not run
1ran
3unverified

Licence: 5 of the 10 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 4 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 1 sample is listed last, in a group without a repository. “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.

CoinCheung/BiSeNet community (archive-listed) 1 sample, 0 ran · 1 unverified
set_model_dist tools/train_amp.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 5c1d86977d83a6be · report
MaybeShewill-CV/bisenetv2-tensorflow community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
compute_iou in 68 papers tools/cityscapes/test_bisenetv2_cityscapes.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 4c9edc2f665fa3ba · report fixture: signature y_pred:ndarray/1/int, y_true:ndarray/1/int, num_classes:int/0/int · returned float64 · level recorded 2026-09-22
decode_prediction_mask tools/cityscapes/test_bisenetv2_cityscapes.py ran · honoured contract fingerprinted MIT (permissive) · f28994d15f099406 · report fixture: signature mask:ndarray/2/int · returned ndarray · level recorded 2026-09-22
gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
calc_bd src/evaluation.py ran · honoured contract fingerprinted no licence file found · pointer only · ad8c528f7eca3b49 · report fixture: signature ins_seg_gt:ndarray/2/int, ins_seg_pred:ndarray/2/int · returned float64 · level recorded 2026-09-22
calc_dic src/evaluation.py ran · violated contract fingerprinted no licence file found · pointer only · 1178cc4faa78d246 · report fixture: signature n_objects_gt:int/0/int, n_objects_pred:int/0/int · returned int64 · level recorded 2026-09-22
calc_dice src/evaluation.py ran · violated contract fingerprinted no licence file found · pointer only · 5f6d96d0e05d3612 · report fixture: signature gt_seg:ndarray/2/float, pred_seg:ndarray/2/float · returned float · level recorded 2026-09-22
hamidriasat/BiSeNetV2 community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
stem_block bisenet_v2.py ran fingerprinted MIT (permissive) · cda3c7e994899232 · report fixture: signature x_in:EagerTensor/4/float, channels:int/0/int · returned EagerTensor · level recorded 2026-09-24
context_embedding_block bisenet_v2.py unverified MIT (permissive) · 6ecfb144dedc8a7a · report
gather_and_expansion_layer bisenet_v2.py unverified MIT (permissive) · bb4d9fdc1dc610e5 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
args_str2bool repository not located ran · violated contract licence of this copy not recorded · eba8919c2ae4a92f · report fixture: signature arg_value:str/0/str · returned bool · level recorded 2026-09-22

Tasks

Real-Time Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation COCO-Stuff BiSeNet V2-Large Frame (fps) 42.5(1080Ti) #1 of 2 Archive leaderboard report
Real-Time Semantic Segmentation COCO-Stuff BiSeNet V2-Large mIoU 28.7 #1 of 2 Archive leaderboard report
Real-Time Semantic Segmentation COCO-Stuff BiSeNet V2 Frame (fps) 87.9(1080Ti) #2 of 2 Archive leaderboard report
Real-Time Semantic Segmentation COCO-Stuff BiSeNet V2 mIoU 25.2 #2 of 2 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2-Large(Cityscapes-Pretrained) Frame (fps) 32.7 #8 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2-Large(Cityscapes-Pretrained) Time (ms) 30.6 #8 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2-Large(Cityscapes-Pretrained) mIoU 78.5 #8 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2(Cityscapes-Pretrained) Frame (fps) 124.5 #10 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2(Cityscapes-Pretrained) Time (ms) 8.0 #10 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2(Cityscapes-Pretrained) mIoU 76.7 #10 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2-Large Frame (fps) 32.7 #17 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2-Large Time (ms) 30.6 #17 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2-Large mIoU 73.2 #17 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2 Frame (fps) 124.5 #19 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2 Time (ms) 8.0 #19 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid BiSeNet V2 mIoU 72.4 #19 of 29 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet V2-Large Frame (fps) 47.3 #14 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet V2-Large Time (ms) 21.1 #14 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet V2-Large mIoU 75.3% #14 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet V2 Frame (fps) 156 #23 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet V2 Time (ms) 6.4 #23 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test BiSeNet V2 mIoU 72.6% #23 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val BiseNetV2-L Frame (fps) 47.3 #15 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val BiseNetV2-L mIoU 75.8% #15 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val BiseNetV2 Frame (fps) 156 #20 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val BiseNetV2 mIoU 73.5% #20 of 24 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

Introduced by this paper: BiSeNet V2, Bilateral Guided Aggregation Layer

1x1 ConvolutionAverage PoolingBatch NormalizationBiSeNet V2Bilateral Guided Aggregation LayerConvolutionDepthwise ConvolutionReLUResidual 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