{"slug": "a-generative-approach-for-improving-multi-label-defect-classification-in-modules", "title": "A Generative Approach for Improving Multi-Label Defect Classification in Photovoltaic Modules", "summary": "Researchers introduced Generative Defect Isolation (GDI), a method using the LaMa inpainting model with Fast Fourier Convolutions to generate realistic single-defect training samples for multi-label defect classification in electroluminescence (EL) images of photovoltaic (PV) cells. Experiments on Vision Transformer (ViT-S, ViT-L) and EfficientNetV2-L architectures showed GDI significantly outperforms baselines, boosting F1-Score for rare defect classes by up to 63.6% and reducing co-occurring classification errors by 26%.", "body_md": "arXiv:2608.12725v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/a-generative-approach-for-improving-multi-label-defect-classification-in-modules", "canonical_source": "https://arxiv.org/abs/2608.12725", "published_at": "2026-08-14 04:00:00+00:00", "updated_at": "2026-08-14 04:06:52.624149+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "generative-ai"], "entities": ["LaMa", "Vision Transformer", "EfficientNetV2-L", "Generative Defect Isolation"], "alternates": {"html": "https://wpnews.pro/news/a-generative-approach-for-improving-multi-label-defect-classification-in-modules", "markdown": "https://wpnews.pro/news/a-generative-approach-for-improving-multi-label-defect-classification-in-modules.md", "text": "https://wpnews.pro/news/a-generative-approach-for-improving-multi-label-defect-classification-in-modules.txt", "jsonld": "https://wpnews.pro/news/a-generative-approach-for-improving-multi-label-defect-classification-in-modules.jsonld"}}