Papers › Self-supervised Pretraining of Visual Features in the Wild

Self-supervised Pretraining of Visual Features in the Wild

2 Mar 2021arXiv:2103.01988archive 2025-07-28

Priya Goyal, Mathilde Caron, Benjamin Lefaudeux, Min Xu, Pengchao Wang, Vivek Pai, Mannat Singh, Vitaliy Liptchinsky, Ishan Misra, Armand Joulin, Piotr Bojanowski

Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods. These results have been achieved in a control environment, that is the highly curated ImageNet dataset. However, the premise of self-supervised learning is that it can learn from any random image and from any unbounded dataset. In this work, we explore if self-supervision lives to its expectation by training large models on random, uncurated images with no supervision. Our final SElf-supERvised (SEER) model, a RegNetY with 1.3B parameters trained on 1B random images with 512 GPUs achieves 84.2% top-1 accuracy, surpassing the best self-supervised pretrained model by 1% and confirming that self-supervised learning works in a real world setting. Interestingly, we also observe that self-supervised models are good few-shot learners achieving 77.9% top-1 with access to only 10% of ImageNet. Code: https://github.com/facebookresearch/vissl

PaperPDFCode

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.

For agents, on Syntology's MCP service (how to connect):

Code

facebookresearch/vissl officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (arXiv:1603.09246; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified), Unsupervised Representation Learning by Predicting Image Rotations (arXiv:1803.07728; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified), BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified) and 1 more (every one in this page's JSON twin); 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationSelf-Supervised Image ClassificationSelf-Supervised LearningSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Places205 SEER Top 1 Accuracy 66.0 #6 of 15 Archive leaderboard report
Image Classification Places205 RegNetY-128GF (Supervised) Top 1 Accuracy 62.7 #9 of 15 Archive leaderboard report
Self-Supervised Image Classification ImageNet SEER Number of Params 1300M #52 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SEER Top 1 Accuracy 77.5% #52 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SEER (RegNetY-256GF) Number of Params 1.3B #33 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SEER (RegNetY-256GF) Top 1 Accuracy 84.2% #33 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SEER (RegNetY-128GF) Number of Params 693M #42 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SEER (RegNetY-128GF) Top 1 Accuracy 83.8% #42 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SEER Large (RegNetY-256GF) Top 1 Accuracy 60.5% #38 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SEER Small (RegNetY-128GF) Top 1 Accuracy 57.5% #43 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SEER Large (RegNetY-256GF) Top 1 Accuracy 77.9% #18 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SEER Small (RegNetY-128GF) Top 1 Accuracy 76.7% #22 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 PoolingBYOLBatch NormalizationBottleneck Residual BlockColorJitterConvolutionCosine AnnealingDense ConnectionsFeedforward NetworkGlobal Average PoolingGradient CheckpointingGrouped ConvolutionInfoNCEKaiming InitializationLARSMax PoolingMoCoNT-XentRandom Gaussian BlurRandom Resized CropReLURegNetYResidual BlockResidual ConnectionSEERSigmoid ActivationSimCLRSqueeze-and-Excitation BlockSwAV

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