A Generative Approach for Improving Multi-Label Defect Classification in Photovoltaic Modules

• URL: http://arxiv.org/abs/2608.12725v1
• Date: Thu, 13 Aug 2026 02:12:57 GMT
• Title: A Generative Approach for Improving Multi-Label Defect Classification in Photovoltaic Modules
• Abstract summary: We introduce Generative Defect Isolation (GDI) to disentangle visual features for specific defect types.<n>Experiments on Vision Transformer (ViT-S) and EfficientNetV2-L architectures demonstrate that GDI significantly outperforms baselines.<n>GDI effectively resolves learning ambiguity from co-occurring defects, yielding a 26% reduction in such co-occurring classification errors.
• Score: 24.555237080546885
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Large-Scale Universal Defect Generation: Foundation Models and Datasets [51.150071370083026]
  We introduce UDG, a large-scale dataset of 300K normal-abnormal-mask-caption quadruplets spanning diverse domains.<n>We present UniDG, a universal defect generation foundation model that supports both reference-based defect generation and text instruction-based defect editing without per-category fine-tuning.<n>Experiments on MVTec-AD and VisA show that UniDG outperforms prior few-shot anomaly generation and image insertion/editing baselines in synthesis quality and downstream single- and multi-class anomaly detection/localization.
  arXiv  Detail & Related papers  (2026-04-10T03:21:17Z)
• Synthetic Defect Image Generation for Power Line Insulator Inspection Using Multimodal Large Language Models [3.72557681438567]
  Utility companies increasingly rely on drone imagery for routine inspection, but training accurate defect-type classifiers remains difficult.<n>We address this data-scarcity setting by using an off-the-shelf multimodal large language model (MLLM) as a training-free image generator.<n>We evaluate on ceramic insulator defect-type classification using a public dataset with a realistic low training-data regime.
  arXiv  Detail & Related papers  (2026-03-09T08:06:27Z)
• Photovoltaic Defect Image Generator with Boundary Alignment Smoothing Constraint for Domain Shift Mitigation [7.166413857036151]
  We propose PDIG, a Photovoltaic Defect Image Generator based on Stable Diffusion (SD)<n>PDIG leverages the strong priors learned from large-scale datasets to enhance generation quality under limited data.<n>Our approach improves Frechet Inception Distance (FID) by 19.16 points over the second-best method.
  arXiv  Detail & Related papers  (2025-05-09T15:16:42Z)
• Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling [61.222803636132554]
  Real-world graph data often exhibit diverse and shifting environments that traditional models fail to generalize across.<n>We propose a novel method termed Multi-Prototype Hyperspherical Invariant Learning (MPHIL)<n>MPHIL achieves state-of-the-art performance, significantly outperforming existing methods across graph data from various domains and with different distribution shifts.
  arXiv  Detail & Related papers  (2025-02-15T07:40:14Z)
• Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background [0.6407952035735353]
  We propose a change-aware Siamese network that solves the defect segmentation in a change detection framework. A novel multi-class balanced contrastive loss is introduced to guide the Transformer-based encoder. The difference presented by a distance map is then skip-connected to the change-aware decoder to assist in the location of both inter-class and out-of-class pixel-wise defects.
  arXiv  Detail & Related papers  (2024-09-01T02:48:11Z)
• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection [106.39544368711427]
  We study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods. We present a novel forgery-aware adaptive transformer approach, namely FatFormer. Our approach tuned on 4-class ProGAN data attains an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.
  arXiv  Detail & Related papers  (2023-12-27T17:36:32Z)
• DiffiT: Diffusion Vision Transformers for Image Generation [88.08529836125399]
  Vision Transformer (ViT) has demonstrated strong modeling capabilities and scalability, especially for recognition tasks. We study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT) DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency.
  arXiv  Detail & Related papers  (2023-12-04T18:57:01Z)
• Deep Learning-Based Defect Classification and Detection in SEM Images [1.9206693386750882]
  In particular, we train RetinaNet models using different ResNet, VGGNet architectures as backbone. We propose a preference-based ensemble strategy to combine the output predictions from different models in order to achieve better performance on classification and detection of defects.
  arXiv  Detail & Related papers  (2022-06-20T16:34:11Z)
• One-Shot Adaptation of GAN in Just One CLIP [51.188396199083336]
  We present a novel single-shot GAN adaptation method through unified CLIP space manipulations. Specifically, our model employs a two-step training strategy: reference image search in the source generator using a CLIP-guided latent optimization. We show that our model generates diverse outputs with the target texture and outperforms the baseline models both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-03-17T13:03:06Z)
• SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation [5.429282997550317]
  We propose a new idea of using generative adversarial network (GAN) for defect segmentation. The GAN-based method removes the defect region in the input defective image to get a defect-free image. To keep the background unchanged before and after image generation, we propose a novel strong identity GAN (SIGAN) The proposed method achieves 90.34% F-score, which outperforms many state-of-the-art methods in terms of solar cell defects segmentation results.
  arXiv  Detail & Related papers  (2021-04-11T08:20:28Z)
• Orthogonal Projection Loss [59.61277381836491]
  We develop a novel loss function termed Orthogonal Projection Loss' (OPL) OPL directly enforces inter-class separation alongside intra-class clustering in the feature space. OPL offers unique advantages as it does not require careful negative mining and is not sensitive to the batch size.
  arXiv  Detail & Related papers  (2021-03-25T17:58:00Z)
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches [67.51747235117]
  Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts. We propose a novel framework for fine-grained visual classification to tackle these problems.
  arXiv  Detail & Related papers  (2020-03-08T19:27:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.