AugOp: Inject Transformation into Neural Operator

TL;DR

AugOp introduces a method to augment convolutional neural networks with group-wise transformations during training, enhancing learning capacity without increasing inference complexity, demonstrated by improved image classification results on CIFAR-10.

Contribution

The paper presents a novel augmentation technique for convolution operators that boosts training performance while maintaining inference efficiency.

Findings

AugResNet outperforms baseline models on CIFAR-10.

The method adds no extra computational cost during inference.

Transformations can be merged with regular convolution without altering topology.

Abstract

In this paper, we propose a simple and general approach to augment regular convolution operator by injecting extra group-wise transformation during training and recover it during inference. Extra transformation is carefully selected to ensure it can be merged with regular convolution in each group and will not change the topological structure of regular convolution during inference. Compared with regular convolution operator, our approach (AugConv) can introduce larger learning capacity to improve model performance during training but will not increase extra computational overhead for model deployment. Based on ResNet, we utilize AugConv to build convolutional neural networks named AugResNet. Result on image classification dataset Cifar-10 shows that AugResNet outperforms its baseline in terms of model performance.