Papers › Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation

Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation

31 May 2024arXiv:2405.20610archive 2025-07-28

WooSeok Shin, Hyun Joon Park, Jin Sob Kim, Sung Won Han

In semi-supervised semantic segmentation, the Mean Teacher- and co-training-based approaches are employed to mitigate confirmation bias and coupling problems. However, despite their high performance, these approaches frequently involve complex training pipelines and a substantial computational burden, limiting the scalability and compatibility of these methods. In this paper, we propose a PrevMatch framework that effectively mitigates the aforementioned limitations by maximizing the utilization of the temporal knowledge obtained during the training process. The PrevMatch framework relies on two core strategies: (1) we reconsider the use of temporal knowledge and thus directly utilize previous models obtained during training to generate additional pseudo-label guidance, referred to as previous guidance. (2) we design a highly randomized ensemble strategy to maximize the effectiveness of the previous guidance. Experimental results on four benchmark semantic segmentation datasets confirm that the proposed method consistently outperforms existing methods across various evaluation protocols. In particular, with DeepLabV3+ and ResNet-101 network settings, PrevMatch outperforms the existing state-of-the-art method, Diverse Co-training, by +1.6 mIoU on Pascal VOC with only 92 annotated images, while achieving 2.4 times faster training. Furthermore, the results indicate that PrevMatch induces stable optimization, particularly in benefiting classes that exhibit poor performance. Code is available at https://github.com/wooseok-shin/PrevMatch

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 11 code samples harvested from 1 repository linked to this paper: 9 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; 6 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (3 with no instrument failure; 6 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 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 9 samples that ran has no recorded date.

wooseok-shin/PrevMatch officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 9 ran (6 instrument-failed) · 2 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

11 samples harvested: 9 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; 6 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; 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
2ran; the contract check could not run
3ran
2unverified

Licence: 6 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 wooseok-shin/PrevMatch. “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.

wooseok-shin/PrevMatch official repository 11 samples, 9 ran (6 instrument-failed) · 2 unverified
ASPPConv in 9 papers model/semseg/deeplabv3plus.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 392d0834780485a1 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, atrous_rate:int/0/int · returned Sequential · level recorded 2026-09-22
conv1x1 in 691 papers model/backbone/resnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 6ef392f365cc5703 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers model/backbone/resnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 794a2ed91a5175bd · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
dataset/transform.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 21e12abf73350be0 · report fixture: signature img:Image/0/?, mask:Image/0/?, size:int/0/int, ignore_value:int/0/int · returned tuple · level recorded 2026-09-26
get_previous_logits prev_utils.py ran Apache-2.0 (permissive) · 7a9f64d049e9d81e · report fixture: signature prev_model_list:list/1/callable, img_u_w:Tensor/2/float, max_num:int/0/int, random_select:bool/0/bool · returned Tensor · level recorded 2026-09-24
hflip in 29 papers dataset/transform.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 9e96d1dddb1f71af · report fixture: signature img:Image/0/?, mask:Image/0/?, p:float/0/float · returned tuple · level recorded 2026-09-26
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
dataset/transform.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 5717ec3a3f33f0a8 · report fixture: signature img:Image/0/?, mask:ndarray/2/int · returned tuple · level recorded 2026-09-26
remove_module_prefix evaluate.py ran · our draft was wrong Apache-2.0 (permissive) · f57298b14577ea23 · report fixture: signature state_dict:dict/0/? · returned dict · level recorded 2026-09-24
setup_distributed in 11 papers util/dist_helper.py ran Apache-2.0 (permissive) · 7c60f8e4d3bbd46f · report fixture: signature backend:str/0/str, port:int/0/int · returned tuple · level recorded 2026-09-24
resnet50 in 121 papers model/backbone/resnet.py unverified Apache-2.0 (permissive) · 1c0a6c3a9a739ec2 · report
xception in 13 papers model/backbone/xception.py unverified Apache-2.0 (permissive) · 73ea75af76a62e43 · report

Tasks

Pseudo LabelSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation COCO 1/128 labeled PrevMatch Validation mIoU 45.7 #3 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation COCO 1/256 labeled PrevMatch Validation mIoU 40.2 #6 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation COCO 1/64 labeled PrevMatch Validation mIoU 48.4 #5 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled PrevMatch (ResNet-101) Validation mIoU 78.9% #3 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled PrevMatch (ResNet-50) Validation mIoU 77.8% #9 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled PrevMatch (ResNet-101) Validation mIoU 80.1% #3 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled PrevMatch (ResNet-50) Validation mIoU 78.8% #11 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled PrevMatch (ResNet-101) Validation mIoU 80.1% #8 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled PrevMatch (ResNet-50) Validation mIoU 79.2% #13 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled PrevMatch (ResNet-101) Validation mIoU 77.7% #3 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled PrevMatch (ResNet-50) Validation mIoU 75.8% #11 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 1464 labels PrevMatch (ResNet-101) Validation mIoU 81.6 #8 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 1464 labels PrevMatch (ResNet-50) Validation mIoU 79.3 #13 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 183 labeled PrevMatch (ResNet-101) Validation mIoU 78.5 #7 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 183 labeled PrevMatch (ResNet-50) Validation mIoU 75.4 #12 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled PrevMatch (ResNet-101) Validation mIoU 80.8 #6 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 366 labeled PrevMatch (ResNet-101) Validation mIoU 79.6 #7 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 366 labeled PrevMatch (ResNet-50) Validation mIoU 77.5 #12 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 732 labeled PrevMatch (ResNet-101) Validation mIoU 80.4 #8 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 732 labeled PrevMatch (ResNet-50) Validation mIoU 78.6 #12 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 92 labeled PrevMatch (ResNet-101) Validation mIoU 77.0 #7 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 92 labeled PrevMatch (ResNet-50) Validation mIoU 73.4 #12 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled PrevMatch (ResNet-101) Validation mIoU 81.9 #5 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled PrevMatch (ResNet-101) Validation mIoU 81.4 #4 of 19 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