ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

In this paper, we introduce an approach to training a given compact network. To this end, we leverage over-parameterization, which typically improves both optimization and generalization in neural network training, while being unnecessary at inference time. We propose to expand each linear layer, both fully-connected and convolutional, of the compact network into multiple linear layers, without adding any nonlinearity. As such, the resulting expanded network can benefit from over-parameterization during training but can be compressed back to the compact one algebraically at inference. We introduce several expansion strategies, together with an initialization scheme, and demonstrate the benefits of our ExpandNets on several tasks, including image classification, object detection, and semantic segmentation. As evidenced by our experiments, our approach outperforms both training the compact network from scratch and performing knowledge distillation from a teacher.