Papers › Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

25 Jul 2018ECCV 2018 9arXiv:1807.09441archive 2025-07-28

Xingang Pan, Ping Luo, Jianping Shi, Xiaoou Tang

Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we present IBN-Net, a novel convolutional architecture, which remarkably enhances a CNN's modeling ability on one domain (e.g. Cityscapes) as well as its generalization capacity on another domain (e.g. GTA5) without finetuning. IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances. This work has three key contributions. (1) By delving into IN and BN, we disclose that IN learns features that are invariant to appearance changes, such as colors, styles, and virtuality/reality, while BN is essential for preserving content related information. (2) IBN-Net can be applied to many advanced deep architectures, such as DenseNet, ResNet, ResNeXt, and SENet, and consistently improve their performance without increasing computational cost. (3) When applying the trained networks to new domains, e.g. from GTA5 to Cityscapes, IBN-Net achieves comparable improvements as domain adaptation methods, even without using data from the target domain. With IBN-Net, we won the 1st place on the WAD 2018 Challenge Drivable Area track, with an mIoU of 86.18%.

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

The archive's official repository (XingangPan/IBN-Net) was not harvested; the 16 samples below come from 2 community repositories.

Syntology 16 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 16 samples from 2 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.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

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

XingangPan/IBN-Net officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
DiegoArcelli/De-Stylization-Network mentioned on GitHubpytorchMITSyntology: not harvested report
Mind23-2/MindCode-52 mentioned on GitHubmindsporeSyntology: not harvested report
WangWenhao0716/DomainMix mentioned on GitHubpytorchSyntology: not harvested report
alibaba/cluster-contrast mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Cluster Contrast for Unsupervised Person Re-Identification (arXiv:2103.11568; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
alibaba/cluster-contrast-reid mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Cluster Contrast for Unsupervised Person Re-Identification (arXiv:2103.11568; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
bupt-ai-cz/hhcl-reid mentioned on GitHubpytorchSyntology: not harvested report
jihaoxuanye/MetaPRD mentioned on GitHubpytorchMITSyntology: 12 samples, 6 ran (1 instrument-failed) · 6 unverified report
leeBooMla/ICSR mentioned on GitHubpytorchSyntology: not harvested report
leeboomla/calr mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified 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
theziqi/dccc mentioned on GitHubpytorchSyntology: not harvested report
wangguangyuan/ClusterContrast mentioned on GitHubpytorchSyntology: not harvested report
wangyuan249/Mymmt767 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
yxgeee/MMT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified) and Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on... (arXiv:2001.01526; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yxgeee/SpCL mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (arXiv:2006.02713; that paper's own run record: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-214 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
Asthestarsfalll/IBNNet-MegEngine pytorchSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
Yang-Q-D/mindsporeCode mindsporeSyntology: not harvested report
code-implementation1/Code4 mindsporeSyntology: not harvested report
layumi/Person_reID_baseline_pytorch pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
thuml/Transfer-Learning-Library pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Domain Adaptation by Backpropagation (arXiv:1409.7495; that paper's own run record: 34 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 12 where Syntology's instrument failed) · 7 unverified), Learning Transferable Features with Deep Adaptation Networks (arXiv:1502.02791; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified), Deep CORAL: Correlation Alignment for Deep Domain Adaptation (arXiv:1607.01719; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified) and 4 more (every one in this page's JSON twin); 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

16 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 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
7ran
8unverified

Licence: 2 of the 16 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 2 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.

jihaoxuanye/MetaPRD community (archive-listed) 12 samples, 6 ran (1 instrument-failed) · 6 unverified
conv3x3 in 1,376 papers mprd/models/resnet_ibn_a.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
output_sim mprd/models/cm.py ran MIT (permissive) · 6f4f409bf7d38cde · report fixture: signature inputs:Tensor/2/float, pos_protomemory:Tensor/2/float, neg_protomemory:Tensor/2/float, targets:Tensor/1/int · returned Tensor · level recorded 2026-09-26
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
mprd/evaluators.py ran MIT (permissive) · b6d5887f94b1db25 · report fixture: signature features:dict/0/?, query:NoneType/0/?, gallery:NoneType/0/? · returned Tensor · level recorded 2026-09-25
process_dir mprd/datasets/dukemtmcreid.py ran fingerprinted MIT (permissive) · 7e822f939fbe184f · report fixture: signature dir_path:str/0/str, relabel:bool/0/bool · returned list · level recorded 2026-09-24
resnet101_ibn_a in 8 papers mprd/models/resnet_ibn_a.py ran MIT (permissive) · c7f5d45660e6ec13 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet50_ibn_a in 10 papers mprd/models/resnet_ibn_a.py ran MIT (permissive) · 93cbdbc352d644d9 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
build_pooling_layer in 6 papers mprd/models/pooling.py unverified MIT (permissive) · 5c5d2f6f3c01ba6c · report
extract_cnn_feature in 14 papers mprd/evaluators.py unverified MIT (permissive) · fbb5efeed7ebfd09 · report
extract_features in 73 papers mprd/evaluators.py unverified MIT (permissive) here; the stored copy is pointer only · 962810c012a60817 · report
g_b_backward mprd/models/cm.py unverified MIT (permissive) · d72cb851db043142 · report
g_backward mprd/models/cm.py unverified MIT (permissive) · cc1f6e8e2a858bb0 · report
label_generator_kmeans in 8 papers mprd/models/kmeans.py unverified MIT (permissive) · 4560dc753fea5981 · report
leeboomla/calr community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
cm in 9 papers calr/models/cm.py ran MIT (permissive) · 6018524d1dc8cbff · report fixture: signature inputs:Tensor/2/float, indexes:Tensor/1/int, features:Tensor/2/float, momentum:float/0/float · returned Tensor · level recorded 2026-09-26
cm_hard in 5 papers calr/models/cm.py ran MIT (permissive) · f435cb7c43ec98ad · report fixture: signature inputs:Tensor/2/float, indexes:Tensor/1/int, features:Tensor/2/float, momentum:float/0/float · returned Tensor · level recorded 2026-09-26
extract_features in 73 papers calr/evaluators.py unverified MIT (permissive) · c27e5ae68871b4b0 · report
extract_features_per_cam calr/evaluators.py unverified MIT (permissive) · e1356bb973ace3a5 · report

Tasks

All-day Semantic SegmentationDomain AdaptationDomain GeneralizationRobust Object DetectionVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
All-day Semantic Segmentation All-day CityScapes IB-Net mIoU 64.5 #3 of 3 Archive leaderboard report
Domain Generalization GTA-to-Avg(Cityscapes,BDD,Mapillary) IBN mIoU 34.63 #22 of 24 Archive leaderboard report
Robust Object Detection DWD IBN-Net mPC [AP50] 25.5 #11 of 12 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 BlockConcatenated Skip ConnectionConvolutionDense BlockDense ConnectionsDropoutGlobal Average PoolingGrouped ConvolutionInstance NormalizationKaiming InitializationMax PoolingReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionSENetSigmoid ActivationSoftmaxSqueeze-and-Excitation Block

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