Papers › Data Distillation: Towards Omni-Supervised Learning

Data Distillation: Towards Omni-Supervised Learning

12 Dec 2017CVPR 2018 6arXiv:1712.04440archive 2025-07-28

Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari, Kaiming He

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lower-bounded by performance on existing labeled datasets, offering the potential to surpass state-of-the-art fully supervised methods. To exploit the omni-supervised setting, we propose data distillation, a method that ensembles predictions from multiple transformations of unlabeled data, using a single model, to automatically generate new training annotations. We argue that visual recognition models have recently become accurate enough that it is now possible to apply classic ideas about self-training to challenging real-world data. Our experimental results show that in the cases of human keypoint detection and general object detection, state-of-the-art models trained with data distillation surpass the performance of using labeled data from the COCO dataset alone.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

EliPassov/classification-ensembles mentioned on GitHubpytorch report
facebookresearch/detectron mentioned on GitHubpytorch report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2 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

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

Tasks

Keypoint DetectionObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionFPNFaster R-CNNMask R-CNNRPNRoIAlignRoIPoolSoftmax

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