Papers › SemPPL: Predicting pseudo-labels for better contrastive representations

SemPPL: Predicting pseudo-labels for better contrastive representations

12 Jan 2023arXiv:2301.05158archive 2025-07-28

Matko Bošnjak, Pierre H. Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic

Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that combines labelled and unlabelled data to learn informative representations. Our method extends self-supervised contrastive learning -- where representations are shaped by distinguishing whether two samples represent the same underlying datum (positives) or not (negatives) -- with a novel approach to selecting positives. To enrich the set of positives, we leverage the few existing ground-truth labels to predict the missing ones through a k-nearest neighbours classifier by using the learned embeddings of the labelled data. We thus extend the set of positives with datapoints having the same pseudo-label and call these semantic positives. We jointly learn the representation and predict bootstrapped pseudo-labels. This creates a reinforcing cycle. Strong initial representations enable better pseudo-label predictions which then improve the selection of semantic positives and lead to even better representations. SemPPL outperforms competing semi-supervised methods setting new state-of-the-art performance of 68.5% and 76% top-1 accuracy when using a ResNet-50 and training on 1% and 10% of labels on ImageNet, respectively. Furthermore, when using selective kernels, SemPPL significantly outperforms previous state-of-the-art achieving 72.3% and 78.3% top-1 accuracy on ImageNet with 1% and 10% labels, respectively, which improves absolute +7.8% and +6.2% over previous work. SemPPL also exhibits state-of-the-art performance over larger ResNet models as well as strong robustness, out-of-distribution and transfer performance. We release the checkpoints and the evaluation code at https://github.com/deepmind/semppl .

PaperPDFCodeCode Syntology ranMethod as code

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 16 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 2 repositories, 12 ran (12 with no instrument failure; 0 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

deepmind/semppl officialmentioned in paperjaxSyntology: 2 samples, 0 ran · 2 unverified report
google-deepmind/semppl officialmentioned in paperjaxApache-2.0Syntology: 14 samples, 12 ran (0 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

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 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.

12ran
4unverified

Licence: 0 of the 16 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 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.

deepmind/semppl official repository 2 samples, 0 ran · 2 unverified
ResNetTorso utils/networks.py unverified Apache-2.0 (permissive) · ec03c773fc93b2dd · report
check_length utils/networks.py unverified Apache-2.0 (permissive) · 05611d15ac79d977 · report
google-deepmind/semppl official repository 14 samples, 12 ran (0 instrument-failed) · 2 unverified
exclude_bias_and_norm in 10 papers utils/optimizers.py ran Apache-2.0 (permissive) · 7cf26db115ac0335 · report fixture: signature path:tuple/1/str, val:ArrayImpl/1/float · returned bool · level recorded 2026-09-25
hsv_to_rgb in 5 papers utils/augmentations.py ran Apache-2.0 (permissive) · 56b9317b9ed66304 · report fixture: signature h:ArrayImpl/2/float, s:ArrayImpl/2/float, v:ArrayImpl/2/float · returned tuple · level recorded 2026-09-25
l2_normalize in 40 papers
census: 15 implementations from 13 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
utils/helpers.py ran Apache-2.0 (permissive) · 8df258170fa3cb79 · report fixture: signature x:ArrayImpl/2/float, axis:NoneType/0/?, epsilon:float/0/float · returned ArrayImpl · level recorded 2026-09-25
learning_schedule utils/schedules.py ran Apache-2.0 (permissive) · 5e9e28416e760f15 · report fixture: signature global_step:ArrayImpl/0/int, batch_size:int/0/int, base_learning_rate:float/0/float, total_steps:int/0/int, warmup_steps:int/0/int · returned ArrayImpl · level recorded 2026-09-25
load_checkpoint in 277 papers utils/checkpointing.py ran fingerprinted Apache-2.0 (permissive) · 5b529484c13fcd15 · report fixture: signature checkpoint_path:str/0/str · returned dict · level recorded 2026-09-25
normalize_images in 8 papers utils/dataset.py ran Apache-2.0 (permissive) · 9299bed7da61102a · report fixture: signature images:ArrayImpl/4/float · returned ArrayImpl · level recorded 2026-09-25
rgb_to_hsv in 5 papers utils/augmentations.py ran Apache-2.0 (permissive) · bf9bb14716c6dab9 · report fixture: signature r:ArrayImpl/2/float, g:ArrayImpl/2/float, b:ArrayImpl/2/float · returned tuple · level recorded 2026-09-25
scale_by_lars utils/optimizers.py ran Apache-2.0 (permissive) · 79415fc4013fff5c · report fixture: signature momentum:float/0/float, eta:float/0/float, filter_fn:callable/0/? · returned GradientTransformation · level recorded 2026-09-25
softmax_cross_entropy in 11 papers utils/helpers.py ran Apache-2.0 (permissive) · 37ae8f08fc24a7d8 · report fixture: signature logits:ArrayImpl/2/float, labels:ArrayImpl/2/float, reduction:str/0/str · returned ArrayImpl · level recorded 2026-09-25
target_ema utils/schedules.py ran Apache-2.0 (permissive) · 8c0e47e0bfa8f06f · report fixture: signature global_step:ArrayImpl/0/int, base_ema:float/0/float, max_steps:int/0/int · returned ArrayImpl · level recorded 2026-09-25
topk_accuracy in 14 papers utils/helpers.py ran Apache-2.0 (permissive) · 73ed5cd901b2ff52 · report fixture: signature logits:ArrayImpl/2/float, labels:ArrayImpl/1/int, topk:int/0/int, ignore_label_above:NoneType/0/? · returned ArrayImpl · level recorded 2026-09-25
transpose_images utils/dataset.py ran Apache-2.0 (permissive) · 301ebdfc332bbcc9 · report fixture: signature batch:dict/0/? · returned dict · level recorded 2026-09-25
add_weight_decay in 27 papers utils/optimizers.py unverified Apache-2.0 (permissive) · 43422aa37e912a67 · report

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. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for SEMPPL (graph method: SEMPPL). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

  1. ResNetTorso entry · level 0 · unverified · ec03c773fc93b2dd
  2. check_length helper · level 0 · unverified · 05611d15ac79d977

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="2301.05158") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningPseudo Label

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockContrastive LearningConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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