# CINIC-10 is not ImageNet or CIFAR-10

Source: [CINIC-10 is not ImageNet or CIFAR-10](<https://www.sota2.com/research/paper/68fa64e11e209131cea07099>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-14T16:58:02.666Z

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

Published: 2018-10-02T21:20:09.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1810.03505>)

[PDF](<https://arxiv.org/pdf/1810.03505.pdf>)

[Implementation](<https://github.com/BayesWatch/cinic-10>)