The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge the dataset by generating samples with generative models. However, their generation quality is still limited by the insufficiency of defect image samples. To this end, we propose Stable Surface Defect Generation (StableSDG), which transfers the vast generation distribution embedded in Stable Diffusion model for steel surface defect image generation. To tackle with the distinctive distribution gap between steel surface images and generated images of the diffusion model, we propose two processes. First, we align the distribution by adapting parameters of the diffusion model, adopted both in the token embedding space and network parameter space. Besides, in the generation process, we propose image-oriented generation rather than from pure Gaussian noises. We conduct extensive experiments on steel surface defect dataset, demonstrating state-of-the-art performance on generating high-quality samples and training recognition models, and both designed processes are significant for the performance.

翻译：钢表面缺陷识别任务是一项具有重要工业价值的工业问题。数据不足是训练鲁棒缺陷识别网络的主要挑战。现有方法尝试通过生成模型生成样本来扩充数据集，但受限于缺陷图像样本的缺乏，其生成质量仍存在局限。为此，我们提出稳定表面缺陷生成方法（StableSDG），该方法将Stable Diffusion模型中蕴含的丰富生成分布迁移至钢表面缺陷图像生成任务。针对钢表面图像与扩散模型生成图像之间的显著分布差异，我们提出两个处理流程：首先通过调整扩散模型的参数实现分布对齐，该方法同时应用于词嵌入空间与网络参数空间；其次在生成过程中，我们提出基于图像导向的生成方式而非从纯高斯噪声出发。在钢表面缺陷数据集上的大量实验表明，本方法在生成高质量样本及训练识别模型方面均达到最优性能，且两个设计流程对性能提升均具有显著意义。