Papers › Label Refinery: Improving ImageNet Classification through Label Progression

Label Refinery: Improving ImageNet Classification through Label Progression

7 May 2018arXiv:1805.02641archive 2025-07-28

Hessam Bagherinezhad, Maxwell Horton, Mohammad Rastegari, Ali Farhadi

Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research. However, studying labels and their properties has received very little attention. Current principles and paradigms of labeling impose several challenges to machine learning algorithms. Labels are often incomplete, ambiguous, and redundant. In this paper we study the effects of various properties of labels and introduce the Label Refinery: an iterative procedure that updates the ground truth labels after examining the entire dataset. We show significant gain using refined labels across a wide range of models. Using a Label Refinery improves the state-of-the-art top-1 accuracy of (1) AlexNet from 59.3 to 67.2, (2) MobileNet from 70.6 to 73.39, (3) MobileNet-0.25 from 50.6 to 55.59, (4) VGG19 from 72.7 to 75.46, and (5) Darknet19 from 72.9 to 74.47.

PaperPDFCode

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

Code

hessamb/label-refinery officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
HoganZhang/label-refinery mentioned on GitHubpytorchNOASSERTION report
Yang-YiFan/DiracDeltaNet mentioned on GitHubpytorch report
chrisqqq123/FA-Dist-EfficientNet mentioned on GitHubpytorch 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

ClassificationGeneral Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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