.png){kind=icon}
返回
Lightweight Deep Neural Network Model With Padding-Free Downsampling
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2024.3374057.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks have achieved impressive performance in image classification tasks. However, due to limitations in hardware resources, including computing units and storage capacity, deploying these networks directly on resource-constrained devices such as mobile and edge devices is challenging. While lightweight network models have made significant advancements, the downsampling stage has received little attention. As the feature map is reused multiple times, the reduction of its size during the downsampling stage not only reduces the computational cost of the downsampling module itself but also lowers the computational burden of subsequent stages. This letter addresses this gap by proposing a padding-free downsampling module that effectively reduces computational costs and can seamlessly integrates into various deep learning models. Furthermore, we introduce a hybrid stem layer to obtain competitive accuracy. Extensive experiments were conducted on CIFAR-100, Stanford Dogs, and ImageNet datasets. On the CIFAR-100 dataset, the results show that the proposed module reduces computational costs by approximately 20% and improves inference speed on resource-constrained devices by around 10%.
Keyword:
Deep learning
image classification
model architecture design
neural network lightweighting
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Damage Detection and Level Classification of Roof Damage After Typhoon Faxai Based on Aerial Photo and Deep Learning基于航拍照片和深度学习的Faxai台风后顶板损伤检测与等级分类.png)
OAAI
IF0
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏KD-LightNet: A Lightweight Network Based on Knowledge Distillation for Industrial Defect Detection
PREAI
分享收藏The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究
OAAI
OAAI分享收藏Computations of Standard Binding Free Energies with Molecular Dynamics Simulations用分子动力学模拟计算标准结合自由能OAAI
OAAI分享收藏
查看更多内容