SOTAVerified

CINIC-10 is not ImageNet or CIFAR-10

2018-10-02Code Available0· sign in to hype

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

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CINIC-10DenseNet-121Accuracy91.26Unverified
CINIC-10ResNeXt29_2x64dAccuracy91.45Unverified
CINIC-10ResNet-18Accuracy90.27Unverified
CINIC-10VGG-16Accuracy87.77Unverified

Reproductions