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

Code

• github.com/PatrykChrabaszcz/Imagenet32_Scripts
  OfficialIn papernone★ 0
• github.com/attaullah/Pretraining-WideResNet
  tf★ 1
• github.com/Prev/downsampled-imagenet-path-fixer
  pytorch★ 0
• github.com/BayesWatch/cinic-10
  pytorch★ 0
• github.com/curryandsun/AIOL
  pytorch★ 0
• github.com/ZilinGao/GM-SOP
  none★ 0

Abstract

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 ImageNet3232 (and its variants ImageNet6464 and ImageNet1616) contains exactly the same number of classes and images as ImageNet, with the only difference that the images are downsampled to 3232 pixels per image (6464 and 1616 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

Tasks

Benchmark Results

Reproductions