가지치기 기반 경량 딥러닝 모델을 활용한 해상객체 이미지 분류에 관한 연구 = A Study on Maritime Object Image Classification Using a Pruning-Based Lightweight Deep-Learning Model

다국어 초록 (Multilingual Abstract)

Deep learning models require high computing power due to a substantial amount of computation. It is difficultto use them in devices with limited computing environments, such as coastal surveillance equipments. In this study,a lightweight model is constructed by analyzing the weight changes of the convolutional layers during the trainingprocess based on MobileNet and then pruning the layers that affects the model less. The performance comparisonresults show that the lightweight model maintains performance while reducing computational load, parameters,model size, and data processing speed. As a result of this study, an effective pruning method for constructinglightweight deep learning models and the possibility of using equipment resources efficiently through lightweightmodels in limited computing environments such as coastal surveillance equipments are presented.

참고문헌 (Reference)

1 Lee K. H., "Trends in Lightweighting Deep Learning Models" Journal of the Society for Information Science 19-20, 2020

2 Sara Elkerdawy, "To Filter Prune, or to Layer Prune, That Is The Question" 2020

3 Li, Hao, "Pruning filters for efficient convnets" 2017

4 Howard, Andrew G., "Mobilenets : Efficient convolutional neural networks for mobile vision applications"

5 Pavlo Molchanov, "Importance Estimation for Neural Network Pruning" 11264-11272, 2019

6 Young A Lee, "Disclosure of North Korean small wooden boat's 'entry into Samcheok Port', government joint investigation results" citizen daily

7 LeCun, "Deep learning" 521 (521): 436-444, 2015

8 Dong-hwi Kim, "A Study on Lightweight and Optimizing with Generative Adversarial Network Based Video Super-resolution Model" 461-463, 2022

9 Moon Kyung Kim, "'Taean smuggling' surveillance equipment was filmed 13 times... the military who could not see and misjudged" YTN