Abstract
Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks
that enables efficient learning and inference. We introduce
LCNN, a lookup-based convolutional neural network that
encodes convolutions by few lookups to a dictionary that is
trained to cover the space of weights in CNNs. Training
LCNN involves jointly learning a dictionary and a small set
of linear combinations. The size of the dictionary naturally
traces a spectrum of trade-offs between efficiency and accuracy. Our experimental results on ImageNet challenge
show that LCNN can offer 3.2× speedup while achieving
55.1% top-1 accuracy using AlexNet architecture. Our
fastest LCNN offers 37.6× speed up over AlexNet while
maintaining 44.3% top-1 accuracy. LCNN not only offers
dramatic speed ups at inference, but it also enables efficient
training. In this paper, we show the benefits of LCNN in
few-shot learning and few-iteration learning, two crucial
aspects of on-device training of deep learning models