Papers › Pushing the limits of self-supervised ResNets: Can we outperform supervised learning...

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?

13 Jan 2022arXiv:2201.05119archive 2025-07-28

Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic

Despite recent progress made by self-supervised methods in representation learning with residual networks, they still underperform supervised learning on the ImageNet classification benchmark, limiting their applicability in performance-critical settings. Building on prior theoretical insights from ReLIC [Mitrovic et al., 2021], we include additional inductive biases into self-supervised learning. We propose a new self-supervised representation learning method, ReLICv2, which combines an explicit invariance loss with a contrastive objective over a varied set of appropriately constructed data views to avoid learning spurious correlations and obtain more informative representations. ReLICv2 achieves 77.1% top-1 accuracy on ImageNet under linear evaluation on a ResNet50, thus improving the previous state-of-the-art by absolute +1.5%; on larger ResNet models, ReLICv2 achieves up to 80.6% outperforming previous self-supervised approaches with margins up to +2.3%. Most notably, ReLICv2 is the first unsupervised representation learning method to consistently outperform the supervised baseline in a like-for-like comparison over a range of ResNet architectures. Using ReLICv2, we also learn more robust and transferable representations that generalize better out-of-distribution than previous work, both on image classification and semantic segmentation. Finally, we show that despite using ResNet encoders, ReLICv2 is comparable to state-of-the-art self-supervised vision transformers.

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 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 13 ran (13 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 between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-deepmind/relicv2 officialmentioned on GitHubjaxApache-2.0Syntology: 14 samples, 13 ran (0 instrument-failed) · 1 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

13ran
1unverified

Licence: 0 of the 14 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 google-deepmind/relicv2. “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.

google-deepmind/relicv2 official repository 14 samples, 13 ran (0 instrument-failed) · 1 unverified
add_weight_decay in 27 papers utils/optimizers.py ran Apache-2.0 (permissive) · 9bc378261f9ad601 · report fixture: signature weight_decay:float/0/float, filter_fn:callable/0/? · returned GradientTransformation · level recorded 2026-09-24
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

Tasks

Image ClassificationLinear evaluationRepresentation LearningSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic SegmentationSemi-Supervised Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ObjectNet RELICv2 Top-1 Accuracy 25.9 #79 of 106 Archive leaderboard report
Image Classification ObjectNet RELIC Top-1 Accuracy 23.8 #84 of 106 Archive leaderboard report
Image Classification ObjectNet BYOL Top-1 Accuracy 23 #85 of 106 Archive leaderboard report
Image Classification ObjectNet SimCLR Top-1 Accuracy 14.6 #99 of 106 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-200 x2) Number of Params 250M #21 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-200 x2) Top 1 Accuracy 80.6% #21 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet200) Number of Params 63M #31 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet200) Top 1 Accuracy 79.8% #31 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-50 4x) Number of Params 375M #34 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-50 4x) Top 1 Accuracy 79.4% #34 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet152) Number of Params 58M #35 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet152) Top 1 Accuracy 79.3% #35 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-50 x2) Number of Params 94M #40 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-50 x2) Top 1 Accuracy 79% #40 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet101) Number of Params 44M #43 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet101) Top 1 Accuracy 78.7% #43 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-50) Number of Params 25M #55 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet ReLICv2 (ResNet-50) Top 1 Accuracy 77.1% #55 of 144 Archive leaderboard report
Semantic Segmentation Cityscapes val ReLICv2 mIoU 75.2 #74 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val BYOL mIoU 74.6 #77 of 99 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val ReLICv2 mIoU 77.9% #14 of 29 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val DetCon mIoU 77.3% #17 of 29 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val BYOL mIoU 75.7% #20 of 29 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data RELICv2 Top 1 Accuracy 58.1% #41 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data RELICv2 Top 5 Accuracy 81.3 #41 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data RELICv2 (ResNet-50) Top 1 Accuracy 72.4% #38 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data RELICv2 (ResNet-50) Top 5 Accuracy 91.2% #38 of 75 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 BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLICReLUResidual 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