Papers › A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

27 Jul 2017arXiv:1707.08819archive 2025-07-28

Patryk Chrabaszcz, Ilya Loshchilov, Frank Hutter

The original ImageNet dataset is a popular large-scale benchmark for training Deep Neural Networks. Since the cost of performing experiments (e.g, algorithm design, architecture search, and hyperparameter tuning) on the original dataset might be prohibitive, we propose to consider a downsampled version of ImageNet. In contrast to the CIFAR datasets and earlier downsampled versions of ImageNet, our proposed ImageNet32×32 (and its variants ImageNet64×64 and ImageNet16×16) contains exactly the same number of classes and images as ImageNet, with the only difference that the images are downsampled to 32×32 pixels per image (64×64 and 16×16 pixels for the variants, respectively). Experiments on these downsampled variants are dramatically faster than on the original ImageNet and the characteristics of the downsampled datasets with respect to optimal hyperparameters appear to remain similar. The proposed datasets and scripts to reproduce our results are available at http://image-net.org/download-images and https://github.com/PatrykChrabaszcz/Imagenet32_Scripts

PaperPDFCode

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

Code

PatrykChrabaszcz/Imagenet32_Scripts officialmentioned in papermentioned on GitHub report
BayesWatch/cinic-10 mentioned on GitHubpytorchMIT report
Prev/downsampled-imagenet-path-fixer mentioned on GitHubpytorch report
ZilinGao/GM-SOP mentioned on GitHub report
curryandsun/AIOL 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

Image ClassificationNeural Architecture Search

Datasets

Introduced by this paper, per the archive.

ImageNet-32ImageNet-64

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet-32 WRN (N=28, k=10) Top 1 Error 40.96 #1 of 1 Archive leaderboard report
Image Classification ImageNet-64 WRN (N=36, k=5) Top 1 Error 32,34% #1 of 1 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.

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