对偶(语法数字)
计算机科学
蒸馏
人工智能
化学
色谱法
艺术
文学类
作者
Wujie Zhou,Jiankang Hong,X. Ran,Weiqing Yan,Qiuping Jiang
出处
期刊:IEEE Transactions on Intelligent Transportation Systems
[Institute of Electrical and Electronics Engineers]
日期:2024-01-01
卷期号:: 1-14
被引量:2
标识
DOI:10.1109/tits.2024.3385744
摘要
Owing to the development of convolutional neural networks (CNNs), the detection of defects on rail surfaces has significantly improved. Although existing methods achieve good results, they incur huge computational and parameter costs associated with CNNs. The usual approach to this problem is to design lightweight models that meet the needs of real-world applications; however, the performance is often compromised. To address the aforementioned problems, we designed a dual semantic approximation network via knowledge distillation (DSANet-KD, a student model with knowledge distillation) for rail surface defect detection; it focuses on both foreground and background knowledge and obtains more accurate prediction results. This model comprises an adaptive 3D spatial integration module, feature-optimization decoding module, and dual semantic approximation knowledge-distillation framework. Specifically, we employed a thoroughly trained teacher defect detection network equipped with dual semantic approximation information as an experienced teacher to guide the training of a student defect detection network. Experimental results showed that the proposed DSANet-KD achieved better accuracy with a smaller number of parameters than the state-of-the-art methods. To demonstrate the generalizability of DSANet-KD, experiments were conducted on a publicly available RGBD-SOD dataset, whose source code is available at: https://github.com/hjklearn/DSANet-KD.
科研通智能强力驱动
Strongly Powered by AbleSci AI