Do Deep Convolutional Nets Really Need to be Deep (Or Even Convolutional)?

Yes, apparently they do. Previous research demonstrated that shallow feed-forward nets sometimes can learn the complex functions previously learned by deep nets while using a similar number of parameters as the deep models they mimic. In this paper we investigate if shallow models can learn to mimic the functions learned by deep convolutional models. We experiment with shallow models and models with a varying number of convolutional layers, all trained to mimic a state-of-the-art ensemble of CIFAR10 models. We demonstrate that we are unable to train shallow models to be of comparable accuracy to deep convolutional models. Although the student models do not have to be as deep as the teacher models they mimic, the student models apparently need multiple convolutional layers to learn functions of comparable accuracy.