Papers › Generative Pretraining from Pixels

Generative Pretraining from Pixels

17 Jul 2020ICML 2020 1archive 2025-07-28

Mark Chen, Alec Radford, Rewon Child, Jeff Wu, Heewoo Jun, Prafulla Dhariwal, David Luan, Ilya Sutskever

Inspired by progress in unsupervised representation learning for natural language, we examine whether similar models can learn useful representations for images. We train a sequence Transformer to auto-regressively predict pixels, without incorporating knowledge of the 2D input structure. Despite training on low-resolution ImageNet without labels, we find that a GPT-2 scale model learns strong image representations as measured by linear probing, fine-tuning, and low-data classification. On CIFAR-10, we achieve 96.3% accuracy with a linear probe, outperforming a supervised Wide ResNet, and 99.0% accuracy with full finetuning, matching the top supervised pre-trained models. An even larger model trained on a mixture of ImageNet and web images is competitive with self-supervised benchmarks on ImageNet, achieving 72.0% top-1 accuracy on a linear probe of our features.

PaperPDFConference PDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

openai/image-gpt officialtfSyntology: not harvested report
EugenHotaj/pytorch-generative pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MADE: Masked Autoencoder for Distribution Estimation (arXiv:1502.03509; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified), Neural Autoregressive Distribution Estimation (arXiv:1605.02226; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Conditional Image Generation with PixelCNN Decoders (arXiv:1606.05328; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
apeguero1/image-gpt tfSyntology: not harvested report
teddykoker/image-gpt pytorchSyntology: not harvested 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 ClassificationRepresentation LearningSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification STL-10 iGPT-L Percentage correct 97.1 #14 of 117 Archive leaderboard report
Image Classification STL-10 AMDIM-L Percentage correct 94.2 #23 of 117 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-XL (64x64, 15360 features) Number of Params 6801M #96 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-XL (64x64, 15360 features) Top 1 Accuracy 72.0% #96 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-XL (64x64, 3072 features) Number of Params 6800M #104 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-XL (64x64, 3072 features) Top 1 Accuracy 68.7% #104 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-L (48x48) Number of Params 1400M #113 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-L (48x48) Top 1 Accuracy 65.2% #113 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-L (32x32) Number of Params 1400M #124 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iGPT-L (32x32) Top 1 Accuracy 60.3% #124 of 144 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 ConvolutionAdamAttentionAverage PoolingBPEBatch NormalizationBottleneck Residual BlockConvolutionCosine AnnealingDense ConnectionsDiscriminative Fine-TuningGPT-2Global Average PoolingKaiming InitializationLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMax PoolingMulti-Head AttentionResidual BlockResidual ConnectionSoftmaxWeight DecayWide Residual BlockWideResNet

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