GhostNet: More Features from Cheap Operations
Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, Chang Xu

TL;DR
GhostNet introduces a novel Ghost module that efficiently generates feature maps from cheap operations, enabling lightweight CNNs with higher accuracy on embedded devices.
Contribution
The paper proposes the Ghost module and GhostNet architecture, which improve feature map generation efficiency and accuracy in lightweight CNNs.
Findings
GhostNet achieves 75.7% top-1 accuracy on ImageNet.
Ghost module outperforms traditional convolution layers in efficiency.
GhostNet surpasses MobileNetV3 in recognition performance with similar computational cost.
Abstract
Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight GhostNet can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
GhostNet: More Features From Cheap Operations· youtube
Taxonomy
TopicsAdvanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Machine Learning and ELM
MethodsSigmoid Activation · ReLU6 · Depthwise Convolution · Pointwise Convolution · Residual Connection · Region Proposal Network · Average Pooling · Focal Loss · Squeeze-and-Excitation Block · Hard Swish
