LCNN: Lookup-based Convolutional Neural Network

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 3.2x 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.

CVPR 17

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Going Deeper with Convolutions
• Compressing Deep Convolutional Networks using Vector Quantization
• Matching Networks for One Shot Learning
• Fully Convolutional Networks for Semantic Segmentation
• Compressing Neural Networks with the Hashing Trick
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Learning Structured Sparsity in Deep Neural Networks
• Bitwise Neural Networks

Cited by in corpus (8)

• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• Channel Pruning for Accelerating Very Deep Neural Networks
• Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
• Adaptive Neural Networks for Efficient Inference
• ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
• WSNet: Compact and Efficient Networks Through Weight Sampling
• Efficient Semantic Segmentation for Visual Bird's-eye View Interpretation