GhostNets on Heterogeneous Devices via Cheap Operations
Kai Han, Yunhe Wang, Chang Xu, Jianyuan Guo, Chunjing Xu, Enhua Wu, Qi, Tian

TL;DR
This paper introduces Ghost modules tailored for heterogeneous mobile devices, enabling efficient CNN deployment by exploiting feature map redundancy to reduce computation and memory usage.
Contribution
The paper proposes novel C-Ghost and G-Ghost modules for CPU and GPU devices, respectively, to improve neural network efficiency through cheap operations and feature redundancy exploitation.
Findings
C-GhostNet achieves high accuracy with low latency on CPU.
G-GhostNet balances accuracy and speed on GPU.
Proposed modules outperform existing lightweight architectures.
Abstract
Deploying convolutional neural networks (CNNs) on mobile devices is difficult due to the limited memory and computation resources. We aim to design efficient neural networks for heterogeneous devices including CPU and GPU, by exploiting the redundancy in feature maps, which has rarely been investigated in neural architecture design. For CPU-like devices, we propose a novel CPU-efficient Ghost (C-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 C-Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. C-Ghost bottlenecks are designed to stack C-Ghost modules, and then the lightweight C-GhostNet can be…
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
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Machine Learning and ELM · Stochastic Gradient Optimization Techniques
