Papers › Exploring the Limits of Weakly Supervised Pretraining

Exploring the Limits of Weakly Supervised Pretraining

2 May 2018ECCV 2018 9arXiv:1805.00932archive 2025-07-28

Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern standards "small". Even so, relatively little is known about the behavior of pretraining with datasets that are multiple orders of magnitude larger. The reasons are obvious: such datasets are difficult to collect and annotate. In this paper, we present a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images. Our experiments demonstrate that training for large-scale hashtag prediction leads to excellent results. We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k single-crop, top-1 accuracy to date: 85.4% (97.6% top-5). We also perform extensive experiments that provide novel empirical data on the relationship between large-scale pretraining and transfer learning performance.

PaperPDFConference PDFCode

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

eminorhan/resnext-wsl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robustness properties of Facebook's ResNeXt WSL models (arXiv:1907.07640; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
facebookresearch/ClassyVision mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified) and An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method. report
facebookresearch/WSL-Images mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: 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

General ClassificationImage ClassificationObject DetectionTransfer Learningimage-classificationobject-detection

Datasets

Introduced by this paper, per the archive.

IG-3.5B-17k

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ResNeXt-101 32x48d GFLOPs 306 #236 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x48d Number of params 829M #236 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x48d Top 1 Accuracy 85.4% #236 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x32d GFLOPs 174 #261 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x32d Number of params 466M #261 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x32d Top 1 Accuracy 85.1% #261 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32×16d GFLOPs 72 #345 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32×16d Number of params 194M #345 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32×16d Top 1 Accuracy 84.2% #345 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x8d Number of params 88M #569 of 1060 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 32x8d Top 1 Accuracy 82.2% #569 of 1060 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 NormalizationConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationRandom Horizontal FlipRandom Resized CropReLUResNeXtResNeXt BlockResidual ConnectionSGD with Momentum

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