@article{turner_distilling_2019,
	title = {Distilling with Performance Enhanced Students},
	url = {https://arxiv.org/abs/1810.10460},
	abstract = {The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy of pruning based approaches has since been called into question. In this paper, we turn to distillation for model compression---specifically, attention transfer---and develop a simple method for discovering performance enhanced student networks. We combine channel saliency metrics with empirical observations of runtime performance to design more accurate networks for a given latency budget. We apply our methodology to residual and densely-connected networks, and show that we are able to find resource-efficient student networks on different hardware platforms while maintaining very high accuracy. These performance-enhanced student networks achieve up to 10\% boosts in top-1 {ImageNet} accuracy over their channel-pruned counterparts for the same inference time.},
	author = {Turner, Jack and Crowley, Elliot J. and Radu, Valentin and Cano, José and Storkey, Amos and O'Boyle, Michael},
	date = {2019-03-07},
	langid = {english},
}