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.

翻译：本文提出了一种简单且通用的方法，通过在训练期间注入额外的分组变换，并在推理期间恢复该变换，来增强常规卷积算子。精心选择额外变换，以确保其能与每组内的常规卷积合并，且不会在推理期间改变常规卷积的拓扑结构。与常规卷积算子相比，我们的方法（AugConv）可在训练期间引入更大的学习能力以提升模型性能，但不会增加模型部署的额外计算开销。基于ResNet，我们利用AugConv构建了名为AugResNet的卷积神经网络。在图像分类数据集Cifar-10上的结果表明，AugResNet在模型性能上优于其基线模型。