Papers › CINIC-10 is not ImageNet or CIFAR-10

CINIC-10 is not ImageNet or CIFAR-10

2 Oct 2018arXiv:1810.03505archive 2025-07-28

Luke N. Darlow, Elliot J. Crowley, Antreas Antoniou, Amos J. Storkey

In this brief technical report we introduce the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10. It was compiled by combining CIFAR-10 with images selected and downsampled from the ImageNet database. We present the approach to compiling the dataset, illustrate the example images for different classes, give pixel distributions for each part of the repository, and give some standard benchmarks for well known models. Details for download, usage, and compilation can be found in the associated github repository.

PaperPDFCode

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

Code

BayesWatch/cinic-10 officialmentioned in papermentioned on GitHubpytorchMIT 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 Classification

Datasets

Introduced by this paper, per the archive.

CINIC-10

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CINIC-10 ResNeXt29_2x64d Accuracy 91.45 #6 of 9 Archive leaderboard report
Image Classification CINIC-10 DenseNet-121 Accuracy 91.26 #7 of 9 Archive leaderboard report
Image Classification CINIC-10 ResNet-18 Accuracy 90.27 #8 of 9 Archive leaderboard report
Image Classification CINIC-10 VGG-16 Accuracy 87.77 #9 of 9 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 NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingReLUResNeXtResNeXt BlockResidual BlockResidual Connection

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