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

27 Jul 2017  ยท  Patryk Chrabaszcz, Ilya Loshchilov, Frank Hutter ยท

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$\times$32 (and its variants ImageNet64$\times$64 and ImageNet16$\times$16) contains exactly the same number of classes and images as ImageNet, with the only difference that the images are downsampled to 32$\times$32 pixels per image (64$\times$64 and 16$\times$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

PDF Abstract

Datasets


Introduced in the Paper:

ImageNet-32 ImageNet-64

Used in the Paper:

CIFAR-10

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification ImageNet-32 WRN (N=28, k=10) Top 1 Error 40.96 # 1
Image Classification ImageNet-64 WRN (N=36, k=5) Top 1 Error 32,34% # 1

Methods


No methods listed for this paper. Add relevant methods here