GhostNeXt: Rethinking Module Configurations for Efficient Model Designopen access
- Authors
- Hong, K.; Kim, G.-H.; Kim, Eun Woo
- Issue Date
- Mar-2023
- Publisher
- MDPI
- Keywords
- module configuration; network design; resource-efficient network
- Citation
- Applied Sciences (Switzerland), v.13, no.5
- Journal Title
- Applied Sciences (Switzerland)
- Volume
- 13
- Number
- 5
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69971
- DOI
- 10.3390/app13053301
- ISSN
- 2076-3417
2076-3417
- Abstract
- Despite the continuous development of convolutional neural networks, it remains a challenge to achieve performance improvement with fewer parameters and floating point operations (FLOPs) as a light-weight model. In particular, excessive expressive power on a module is a crucial cause of skyrocketing the computational cost of the entire network. We argue that it is necessary to optimize the entire network by optimizing single modules or blocks of the network. Therefore, we propose GhostNeXt, a promising alternative to GhostNet, by adjusting the module configuration inside the Ghost block. We introduce a controller to select channel operations of the module dynamically. It holds a plug-and-play component that is more useful than the existing approach. Experiments on several classification tasks demonstrate that the proposed method is a better alternative to convolution layers in baseline models. GhostNeXt achieves competitive recognition performance compared to GhostNet and other popular models while reducing computational costs on the benchmark datasets. © 2023 by the authors.
- Files in This Item
-
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69971)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.