Semi-supervised Learning for Photovoltaic Cell Defect Detection Using Module and Cell-Level Labels

Defect detection in photovoltaic (PV) modules is crucial for ensuring energy efficiency and long-term performance. Traditionally, electroluminescence (EL) images have been manually analyzed by workers, leading to inefficiencies and subjectivity in the inspection process. To address these issues, deep learning algorithms, such as convolutional neural networks (CNN), have been employed, but most of these approaches using only module-level labels restrict defect detection to the module level and lack precision in identifying defective cells. On the other hand, methods relying solely on cell-level labels can detect defects at the cell-level but they require extensive annotation, making them impractical for industrial applications. To overcome these limitations, we propose a novel two-stage learning method that combines module-level and cell-level labels for training. Our approach applies semi-supervised learning to improve defect detection performance at both the module and cell levels, with a limited number of cell-level labels. Experimental results on the same dataset demonstrate that our method outperforms traditional approaches relying on single-level labels, achieving superior performance.