报告详情
An Adaptive Structured Pruning Framework for Efficient Neural Network Inference on Resource-Constrained Edge Devices
编号：42
访问权限：仅限参会人
更新：2026-10-04 23:23:58 浏览：7次
Online
报告开始：2026年10月13日 15:15（Asia/Ho_Chi_Minh）
报告时间：15min
所在会场：[S5] Track 5: Emerging Trends of AI/ML [S5-6] Track 5: Emerging Trends of AI/ML
暂无文件
摘要
Deep neural networks have been proven effective in computer vision tasks like image classification, object detection, and many other AI applications. Yet, the computational and memory requirements of these models make them hard to deploy on edge devices that have limited resources. Neural network pruning is an effective model compression technique that involves removing less important parameters or structural components of a trained model. We propose an adaptive structured pruning method that allows reduction of the complexity of a neural network without compromising too much on performance. In this method, first filters are ranked based on their contribution to the network and then low-importance ones are removed gradually. After that, a short fine-tuning period is done to get back some of the accuracy that was lost during pruning. The whole method is assessed through the model size, parameter reduction, FLOPs, inference latency, and classification accuracy metrics. Findings of this study revealed that a 50% structured pruning can significantly decrease the number of parameters and operations but still preserve an accuracy level of the original model. A comparison is provided between structured and unstructured pruning with the reasons of why structured pruning is more appropriate for actual edge hardware. It is concluded that pruning can be further combined with quantization and hardware-aware optimization methods through which more improvements can be made.
关键词
Neural Network Pruning,Deep Learning,model compression
报告人
Harinagapraveen Gundugolanu
Data analyst Industry稿件作者
全部评论
重要日期
-
会议日期
10月11日
2026
至10月14日
2026
-
12月30日 2025
报告提交截止日期
-
09月28日 2026
提前注册日期
-
10月10日 2026
初稿截稿日期
-
10月14日 2026
注册截止日期
主办单位
United Societies of Science
承办单位
Posts and Telecommunications Institute of Technology
协办单位
IEEE Section
IEEE Vietnam Section
IEEE Vietnam Section
联系方式
- ASIANComNet 2026
- as******@usssociety.org
发表评论