Joint Detection Model Based on YOLOv5 to Detect Lithium Battery Defects with Noisy Label
Chao Yao, Xiongwen Pang, Xundi Huang, Hai Kuang · 2022
Data-driven intelligent detection methods have been widely used in the detection of defects in lithium batteries, with outstanding results. However, there are situations of inaccurate labeling due to category similarity in the labeling process, resulting in noisy labels that subsequently influence the model's prediction. To solve this problem, we propose a joint detection model based on YOLOv5, in which the whole is decoupled into two main parts, i.e., a fully supervised detection model and a semi-supervised classification model which uses clustering to divide the data. These two parts can effectively focus on key domains so as to attenuate the impact of noise labels under the relevant domains, and achieve overall noise immunity by connecting detection with classification in the validation phase. The approach outperforms the native YOLOv5 ([email protected] as metric) by 5.7 percent, 10.2 percent, and 10.7 percent at 10%, 20%, and 30% noise fractions, respectively.