修剪
冗余(工程)
频道(广播)
计算机科学
人工智能
目标检测
计算
卷积(计算机科学)
失败
模式识别(心理学)
数据挖掘
算法
生物
人工神经网络
计算机网络
并行计算
农学
操作系统
作者
Changcai Yang,Zhiping Lin,Ziyang Lan,Riqing Chen,Lifang Wei,Yizhang Liu
标识
DOI:10.1016/j.knosys.2024.111432
摘要
Real-time object detection plays a crucial role in edge devices applications. Pruning methods are usually used to effectively eliminate redundant parameters of the object detection network so that it can detect objects efficiently. However, traditional pruning methods often result in a significant drop in accuracy, requiring time-consuming fine-tuning to restore the accuracy of the network. To address this issue, we propose an evolutionary channel pruning (ECP) method to reduce the redundant parameters in the network. Our proposed ECP method effectively reduces parameter redundancy and computation complexity in object detection networks while maintaining detection accuracy. Additionally, we introduce a novel Channel Information Mixing Convolution (CIMConv) that leverages more cost-effective operations to achieve higher accuracy and reduce the complexity associated with standard convolution. By applying our proposed ECP and CIMConv to the existing object detection methods, we achieve a superior balance between accuracy and complexity compared to state-of-the-art detectors. Notably, on challenging public datasets such as GTSDB, S2TLD, TT100K, Wider Face, and Microsoft COCO, our proposed ECP substantially decrease the number of parameters and FLOPs of YOLOv5, simultaneously improving detection accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI