Augmentation Inside the Network
This work offers an incremental improvement in efficiency and performance for computer vision practitioners using data augmentation, particularly at test time.
This paper introduces "augmentation inside the network," a method that applies data augmentation techniques to intermediate features within a convolutional neural network. The approach achieves a smoother speed-accuracy trade-off and outperforms standard test-time augmentation (TTA), with a modification being 30% faster than flip TTA while maintaining performance on CIFAR-100.
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.