Photovoltaic Defect Image Generator with Boundary Alignment Smoothing Constraint for Domain Shift Mitigation

TL;DR

This paper introduces PDIG, a novel photovoltaic defect image generator that uses stable diffusion with boundary alignment and domain adaptation techniques to improve defect dataset quality and enhance defect detection accuracy.

Contribution

The paper presents a new PV defect image generator leveraging stable diffusion, semantic concept embedding, and style adaptation to address data scarcity and domain shift issues.

Findings

Improves FID by 19.16 points over previous methods.

Enhances defect detection performance significantly.

Generates more realistic and diverse defect images.

Abstract

Accurate defect detection of photovoltaic (PV) cells is critical for ensuring quality and efficiency in intelligent PV manufacturing systems. However, the scarcity of rich defect data poses substantial challenges for effective model training. While existing methods have explored generative models to augment datasets, they often suffer from instability, limited diversity, and domain shifts. To address these issues, we propose PDIG, a Photovoltaic Defect Image Generator based on Stable Diffusion (SD). PDIG leverages the strong priors learned from large-scale datasets to enhance generation quality under limited data. Specifically, we introduce a Semantic Concept Embedding (SCE) module that incorporates text-conditioned priors to capture the relational concepts between defect types and their appearances. To further enrich the domain distribution, we design a Lightweight Industrial Style Adaptor (LISA), which injects industrial defect characteristics into the SD model through cross-disentangled attention. At inference, we propose a Text-Image Dual-Space Constraints (TIDSC) module, enforcing the quality of generated images via positional consistency and spatial smoothing alignment. Extensive experiments demonstrate that PDIG achieves superior realism and diversity compared to state-of-the-art methods. Specifically, our approach improves Frechet Inception Distance (FID) by 19.16 points over the second-best method and significantly enhances the performance of downstream defect detection tasks.