LCNN: Lookup-Based Convolutional Neural Network
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017)
摘要
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 3.2x speedup while achieving 55.1% top-1 accuracy using AlexNet architecture. Our fastest LCNN offers 37.6x 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.
更多查看译文
关键词
few-shot learning,few-iteration learning,deep learning models,constrained compute platforms,LCNN training,lookup-based convolutional neural network,AlexNet architecture
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要