earticle

논문검색

Oral Session I AI : 영상 분석

채널 프루닝과 전이 학습을 이용한 경량 DNN 모델 개발

원문정보

Development of a Lightweight DNN Model using channel Pruning with Transfer Learning

Sara Sualiheen, Deok-Hwan Kim

피인용수 : 0(자료제공 : 네이버학술정보)

초록

영어

Deep neural networks (DNNs) have been widely used in various applications, however, the computational complexity and memory requirements of DNNs are becoming increasingly challenging, especially in resource-constrained devices such as mobile phones and embedded systems. In this paper, we propose a lightweight DNN model using channel pruning to address the computational complexity and memory requirements of DNNs in resource-constrained devices. Our approach combines channel pruning with transfer learning to maintain accuracy. Evaluation on the CIFAR-10 dataset shows improved performance with 78% test accuracy, 89% train accuracy, and 73% validation accuracy compared to the unpruned model. The pruned model is suitable for applications with limited computational resources.

목차

Abstract
1. Introduction
2. Related Works
3. Proposed Methodology
3.1. Proposed Framework
4. Experiments
4.1. Experimental setup
4.2. Dataset
4.3. Experimental result
5. Conclusions
Acknowledgment
References

저자정보

  • Sara Sualiheen Department of Electrical and Computer Engineering Inha University, Incheon, South Korea
  • Deok-Hwan Kim Department of Electrical and Computer Engineering Inha University, Incheon, South Korea

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      0개의 논문이 장바구니에 담겼습니다.