Papers › ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning

ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning

15 Jul 2020arXiv:2007.07936archive 2025-07-28

Viktor Olsson, Wilhelm Tranheden, Juliano Pinto, Lennart Svensson

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for training, which sometimes requires hours of manual labor for a single image. Because of this, semi-supervised methods have been applied to this task, with varying degrees of success. A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation. We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network's predictions for respecting object boundaries. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-the-art results. Lastly, we also provide extensive ablation studies comparing different design decisions and training regimes.

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 19 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 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: official repository: 19 samples from 1 repository, 12 ran (10 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

WilhelmT/ClassMix officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 12 ran (2 instrument-failed) · 7 unverified report
lorenmt/reco mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bootstrapping Semantic Segmentation with Regional Contrast (arXiv:2104.04465; that paper's own run record: 3 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; 0 where Syntology's instrument failed) · 3 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

19 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 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 · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
7ran
7unverified

Licence: 4 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 WilhelmT/ClassMix. “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.

WilhelmT/ClassMix official repository 19 samples, 12 ran (2 instrument-failed) · 7 unverified
color_map in 15 papers evaluateSSL.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · fcbd501f30a007d4 · report fixture: signature N:int/0/int, normalized:bool/0/bool · returned ndarray · level recorded 2026-09-22
colorize_mask in 21 papers utils/helpers.py ran MIT (permissive) · 980e8f8763638799 · report fixture: signature mask:ndarray/2/int, palette:list/1/int · returned Image · level recorded 2026-09-25
conv3x3 in 1,376 papers model/deeplabv2.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
customsoftmax utils/loss.py ran fingerprinted MIT (permissive) · d6015f0e8b0685cc · report fixture: signature inp:Tensor/2/float, multihotmask:Tensor/2/float · returned Tensor · level recorded 2026-09-25
flip in 32 papers
census: 3 implementations from 5 papers, 2 distinct outputs on one shared input
utils/transformsgpu.py ran MIT (permissive) · 79963969c998c40d · report fixture: signature flip:int/0/int, data:Tensor/4/float, target:Tensor/3/float · returned tuple · level recorded 2026-09-25
generate_cow_mask utils/transformmasks.py ran MIT (permissive) · db898bc1ff25e367 · report fixture: signature img_size:tuple/1/int, sigma:float/0/float, p:float/0/float, seed:int/0/int · returned ndarray · level recorded 2026-09-25
generate_cutout_mask utils/transformmasks.py ran MIT (permissive) · 50a4b555e559ce5e · report fixture: signature img_size:tuple/1/int, seed:int/0/int · returned ndarray · level recorded 2026-09-25
get_label_vector in 6 papers evaluateSSL.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 799a094d0124a46c · report fixture: signature target:ndarray/1/int, nclass:int/0/int · returned ndarray · level recorded 2026-09-22
get_voc_palette utils/palette.py ran fingerprinted MIT (permissive) · d46e561fba210e1a · report fixture: signature num_classes:int/0/int · returned list · level recorded 2026-09-25
lr_poly in 25 papers trainSSL.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · b3b7c1c716f4ca66 · report fixture: signature base_lr:float/0/float, iter:int/0/int, max_iter:int/0/int, power:float/0/float · returned float · level recorded 2026-09-22
outS in 12 papers model/deeplabv2.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 27504cbeb5811ea6 · report fixture: signature i:int/0/int · returned float · level recorded 2026-09-22
sigmoid_ramp_up trainSSL.py ran fingerprinted MIT (permissive) · d4002df13f6d42ed · report fixture: signature iter:int/0/int, max_iter:int/0/int · returned float64 · level recorded 2026-09-25
Res_Deeplab in 7 papers model/deeplabv2.py unverified MIT (permissive) · 68fab2021abbbebf · report
colorJitter utils/transformsgpu.py unverified MIT (permissive) · bb18b872b207d4a2 · report
convert_model in 14 papers utils/sync_batchnorm/batchnorm.py unverified MIT (permissive) · b0cd1f9681d630e2 · report
gaussian_blur in 17 papers utils/transformsgpu.py unverified MIT (permissive) · b36157ea719029fe · report
generate_class_mask utils/transformmasks.py unverified MIT (permissive) · 78c73917d17c705c · report
get_iou in 34 papers evaluateSSL.py unverified MIT (permissive) · fb1d8f93c75b5433 · report
get_upsampling_weight in 13 papers utils/helpers.py unverified MIT (permissive) · 623804a7cb75739e · report

Tasks

Data AugmentationSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 100 samples labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 54.07% #12 of 13 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 61.35% #30 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 2% labeled ClassMix (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 52.14% #2 of 3 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 63.63% #28 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 5% labeled ClassMix (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 58.77% #2 of 3 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 66.29% #22 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 72.45 #25 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 1% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 54.18% #5 of 6 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled ClassMix Validation mIoU 71.00% #30 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 2% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 66.15% #7 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 5% labeled ClassMix (DeepLab v2 MSCOCO pretrained) Validation mIoU 67.77% #9 of 14 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