Skip to content

mil-tokyo/bc_learning_image

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BC learning for images

Implementation of Between-class Learning for Image Classification by Yuji Tokozume, Yoshitaka Ushiku, and Tatsuya Harada.

Our preliminary experimental results on CIFAR-10 and ImageNet-1K were already presented in ILSVRC2017 on July 26, 2017.

Between-class (BC) learning:

Contents

  • BC learning for images
    • BC: mix two images simply using internal divisions.
    • BC+: mix two images treating them as waveforms.
  • Training of 11-layer CNN on CIFAR datasets

Setup

  • Install Chainer v1.24 on a machine with CUDA GPU.
  • Prepare CIFAR datasets.

Training

  • Template:

      python main.py --dataset [cifar10 or cifar100] --netType convnet --data path/to/dataset/directory/ (--BC) (--plus)
    
  • Recipes:

    • Standard learning on CIFAR-10 (around 6.1% error):

        python main.py --dataset cifar10 --netType convnet --data path/to/dataset/directory/
      
    • BC learning on CIFAR-10 (around 5.4% error):

        python main.py --dataset cifar10 --netType convnet --data path/to/dataset/directory/ --BC
      
    • BC+ learning on CIFAR-10 (around 5.2% error):

        python main.py --dataset cifar10 --netType convnet --data path/to/dataset/directory/ --BC --plus
      
  • Notes:

    • It uses the same data augmentation scheme as fb.resnet.torch.
    • By default, it runs training 10 times. You can specify the number of trials by using --nTrials command.
    • Please check opts.py for other command line arguments.

Results

Error rate (average of 10 trials)

Learning CIFAR-10 CIFAR-100
Standard 6.07 26.68
BC (ours) 5.40 24.28
BC+ (ours) 5.22 23.68
  • Other results (please see paper):
    • The performance of Shake-Shake Regularization [1] on CIFAR-10 was improved from 2.86% to 2.26%.
    • The performance of ResNeXt [2] on ImageNet-1K was improved from 20.4% to 19.4% (single-crop top-1 validation error).

Reference

[1] X. Gastaldi. Shake-shake regularization. In ICLR Workshop, 2017.

[2] S. Xie, R. Girshick, P. Dollar, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. In CVPR, 2017.

About

Chainer implementation of between-class learning for Image classification https://arxiv.org/abs/1711.10284

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages