TL;DR: This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with model distillation and heavy hyperparameter optimization.
Abstract: Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-forward nets sometimes can learn the complex functions previously learned by deep nets while using the same number of parameters as the deep models they mimic, in this paper we demonstrate that the same methods cannot be used to train accurate models on CIFAR-10 unless the student models contain multiple layers of convolution. Although the student models do not have to be as deep as the teacher model they mimic, the students need multiple convolutional layers to learn functions of comparable accuracy as the deep convolutional teacher.
Keywords: Deep learning, Transfer Learning
Conflicts: uci.edu, sms.ed.ac.uk, polymtl.ca, cs.ualberta.ca, cs.washington.edu, microsoft.com, uni-heidelberg.de, mpimf-heidelberg.mpg.de
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:1603.05691/code)