文献类型：期刊文献

英文题名：LFLD-CLbased NET: A Curriculum-Learning-Based Deep Learning Network with Leap-Forward-Learning-Decay for Ship Detection

作者：Li, Jiawen[1,2,3];Sun, Jiahua[1];Li, Xin[1];Yang, Yun[1,4];Jiang, Xin[1];Li, Ronghui[1,2,3]

机构：[1]Guangdong Ocean Univ, Naval Architecture & Shipping Coll, Zhanjiang 524005, Peoples R China;[2]Tech Res Ctr Ship Intelligence & Safety Engn Guang, Zhanjiang 524005, Peoples R China;[3]Guangdong Prov Key Lab Intelligent Equipment South, Zhanjiang 524005, Peoples R China;[4]Shenzhen Univ, Coll Civil & Transportat Engn, Shenzhen 518060, Peoples R China

年份：2023

卷号：11

期号：7

外文期刊名：JOURNAL OF MARINE SCIENCE AND ENGINEERING

收录：SCI-EXPANDED(收录号：WOS:001038571200001)、、Scopus(收录号：2-s2.0-85166229236)、WOS

基金：This research was funded by the Ocean Young Talent Innovation Programme of Zhanjiang City (Grant No. 2022E05002), the Young Innovative Talents Grants Programme of Guangdong Province (Grant No. 2022KQNCX024), the National Natural Science Foundation of China (Grant No. 52171346), the Natural Science Foundation of Guangdong Province (Grant No. 2021A1515012618), and the special projects of key fields (Artificial Intelligence) of Universities in Guangdong Province (Grant No. 2019KZDZX1035), the program for scientific research start-up funds of Guangdong Ocean University, and the College Student Innovation Team of Guangdong Ocean University (Grant No. CXTD2021013).

语种：英文

外文关键词：ship detection; vessel monitoring; deep learning; curriculum learning; learning rate decay

外文摘要：Ship detection in the maritime domain awareness field has seen a significant shift towards deep-learning-based techniques as the mainstream approach. However, most existing deep-learning-based ship detection models adopt a random sampling strategy for training data, neglecting the complexity differences among samples and the learning progress of the model, which hinders training efficiency, robustness, and generalization ability. To address this issue, we propose a ship detection model called the Leap-Forward-Learning-Decay and Curriculum Learning-based Network (LFLD-CLbased NET). This model incorporates innovative strategies as Leap-Forward-Learning-Decay and curriculum learning to enhance its ship detection capabilities. The LFLD-CLbased NET is composed of ResNet as the feature extraction unit, combined with a difficulty generator and a difficulty scheduler. The difficulty generator in LFLD-CLbased NET effectively expands data samples based on real ocean scenarios, and the difficulty scheduler constructs corresponding curriculum training data, enabling the model to be trained in an orderly manner from easy to difficult. The Leap-Forward-Learning-Decay strategy, which allows for flexible adjustment of the learning rate during curriculum training, is proposed for enhancing training efficiency. Our experimental findings demonstrate that our model achieved a detection accuracy of 86.635%, approximately 10% higher than other deep-learning-based ship detection models. In addition, we conducted extensive supplementary experiments to evaluate the effectiveness of the learning rate adjustment strategy and curriculum training in ship detection tasks. Furthermore, we conducted exploratory experiments on different modules to compare performance differences under varying parameter configurations.