A Large-scale Evaluation of Pretraining Paradigms for the Detection of Defects in Electroluminescence Solar Cell Images
This work addresses the challenge of limited labelled data for defect detection in solar cell images, providing benchmarks and datasets to advance research in this domain-specific area.
The paper tackled the problem of detecting defects in electroluminescence solar cell images by evaluating various pretraining methods, achieving a new state-of-the-art in Solar Cell Defect Detection with statistically equivalent performance across supervised, self-supervised, and semi-supervised techniques in terms of mean Intersection over Union (mIoU).
Pretraining has been shown to improve performance in many domains, including semantic segmentation, especially in domains with limited labelled data. In this work, we perform a large-scale evaluation and benchmarking of various pretraining methods for Solar Cell Defect Detection (SCDD) in electroluminescence images, a field with limited labelled datasets. We cover supervised training with semantic segmentation, semi-supervised learning, and two self-supervised techniques. We also experiment with both in-distribution and out-of-distribution (OOD) pretraining and observe how this affects downstream performance. The results suggest that supervised training on a large OOD dataset (COCO), self-supervised pretraining on a large OOD dataset (ImageNet), and semi-supervised pretraining (CCT) all yield statistically equivalent performance for mean Intersection over Union (mIoU). We achieve a new state-of-the-art for SCDD and demonstrate that certain pretraining schemes result in superior performance on underrepresented classes. Additionally, we provide a large-scale unlabelled EL image dataset of $22000$ images, and a $642$-image labelled semantic segmentation EL dataset, for further research in developing self- and semi-supervised training techniques in this domain.