English

Augmentation Inside the Network

Computer Vision and Pattern Recognition 2023-06-27 v2 Machine Learning Neural and Evolutionary Computing

Abstract

In this paper, we present augmentation inside the network, a method that simulates data augmentation techniques for computer vision problems on intermediate features of a convolutional neural network. We perform these transformations, changing the data flow through the network, and sharing common computations when it is possible. Our method allows us to obtain smoother speed-accuracy trade-off adjustment and achieves better results than using standard test-time augmentation (TTA) techniques. Additionally, our approach can improve model performance even further when coupled with test-time augmentation. We validate our method on the ImageNet-2012 and CIFAR-100 datasets for image classification. We propose a modification that is 30% faster than the flip test-time augmentation and achieves the same results for CIFAR-100.

Keywords

Cite

@article{arxiv.2012.10769,
  title  = {Augmentation Inside the Network},
  author = {Maciej Sypetkowski and Jakub Jasiulewicz and Zbigniew Wojna},
  journal= {arXiv preprint arXiv:2012.10769},
  year   = {2023}
}
R2 v1 2026-06-23T21:06:03.696Z