一种用于改进光伏组件多标签缺陷分类的生成式方法
A Generative Approach for Improving Multi-Label Defect Classification in Photovoltaic Modules
查看机构详情
- University of Central Florida（中佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文针对光伏组件EL图像多标签缺陷分类的挑战，提出生成式缺陷隔离（GDI）方法，利用带快速傅里叶卷积的LaMa模型生成单缺陷样本，在多种模型上使罕见缺陷F1分数最高提升63.6%，共存分类错误降低26%，为该领域多标签分类设定新基准。
中文摘要 AI 辅助
本文针对光伏（PV）电池的电致发光（EL）图像中多标签缺陷分类的挑战展开研究。在存在多种缺陷共存的图像上训练模型会产生学习歧义，导致难以区分特定缺陷类型的视觉特征，而各类别样本稀缺的问题进一步加剧了这一状况。为解决该问题，我们提出了生成式缺陷隔离（Generative Defect Isolation, GDI）方法，利用带有快速傅里叶卷积的LaMa图像修复模型移除选定的缺陷并生成逼真的单缺陷训练样本。在Vision Transformer（ViT-S、ViT-L）和EfficientNetV2-L架构上进行的大量实验表明，GDI的性能显著优于基线方法。在低数据场景下，性能提升最为明显；按类别分析显示，GDI实现了大幅改进，使罕见缺陷类别的F1分数提升最高达63.6%。此外，GDI有效解决了共存缺陷带来的学习歧义，使此类共存分类错误降低了26%。本研究确立了GDI作为最大化现有分割数据集价值的有效方法，并为该领域的多标签分类设定了新的性能基准。
英文摘要
This paper addresses the challenge of multi-label defect classification in electroluminescence (EL) images of photovoltaic (PV) cells. Training models on images where multiple defects co-occur creates learning ambiguity, making it difficult to disentangle visual features for specific defect types, a problem compounded by the scarcity of examples for individual classes. To tackle this, we introduce Generative Defect Isolation (GDI), utilizing the LaMa inpainting model with Fast Fourier Convolutions to remove selected defects and generate realistic, single-defect training samples. Extensive experiments on Vision Transformer (ViT-S, ViT-L) and EfficientNetV2-L architectures demonstrate that GDI significantly outperforms baselines. The performance gains are most pronounced in low-data scenarios; class-wise analysis shows substantial improvements, boosting the F1-Score for rare defect classes by up to 63.6%. Furthermore, GDI effectively resolves learning ambiguity from co-occurring defects, yielding a 26% reduction in such co-occurring classification errors. Our work establishes GDI as an effective method for maximizing the value of existing segmentation datasets and sets a new performance benchmark for multi-label classification in this domain.
