Learning Efficient Convolutional Networks through Network Slimming

ICCV 2017 Zhuang LiuJianguo LiZhiqiang ShenGao HuangShoumeng YanChangshui Zhang

The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the model size; 2) decrease the run-time memory footprint; and 3) lower the number of computing operations, without compromising accuracy... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Neural Architecture Search CIFAR-10 Image Classification DARTS + c/o Percentage error 2.83 # 5
Neural Architecture Search CIFAR-10 Image Classification DARTS + c/o Params 3.4M # 1