Papers › Exploring the Limits of Weakly Supervised Pretraining
Exploring the Limits of Weakly Supervised Pretraining
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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