Papers › Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
Hai-Ming Xu, Lingqiao Liu, Qiuchen Bian, Zhen Yang
Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation, i.e., regions belonging to the same class may exhibit a very different appearance even in the same picture. This diversity will make the label propagation hard from pixels to pixels. To address this problem, we propose a novel approach to regularize the distribution of within-class features to ease label propagation difficulty. Specifically, our approach encourages the consistency between the prediction from a linear predictor and the output from a prototype-based predictor, which implicitly encourages features from the same pseudo-class to be close to at least one within-class prototype while staying far from the other between-class prototypes. By further incorporating CutMix operations and a carefully-designed prototype maintenance strategy, we create a semi-supervised semantic segmentation algorithm that demonstrates superior performance over the state-of-the-art methods from extensive experimental evaluation on both Pascal VOC and Cityscapes benchmarks.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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.
Syntology holds a reference implementation of Prototype-based Consistency Regularization, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Prototype-based Consistency Regularization') (how to connect); the free check have('2210.04388') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2210.04388", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2210.04388")
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
1 assembly on this paper: 0 harvested, 1 generated.
generated Assembly for Prototype-based Consistency Regularization (graph method: Prototype-based Consistency Regularization), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).
label matches by construction: the code was generated for this method (not judged by a model)
- update_prototypes_ema entry · level 2 · ran ·
e5c88f51fd471dab3c7775ceda41299f69399fdfb1b12384d49e7173357d7d3c
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2210.04388") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Semantic Segmentation | Cityscapes 12.5% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 76.31% | #17 of 33 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 25% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 78.4% | #15 of 30 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 50% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 79.11% | #15 of 23 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 6.25% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 73.41% | #14 of 18 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 25% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 80.78 | #7 of 27 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 50% | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 80.91% | #2 of 14 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Pascal VOC 2012 12.5% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 80.71% | #8 of 38 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Pascal VOC 2012 6.25% labeled | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | Validation mIoU | 78.6 | #9 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.
Methods
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