DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learning
This addresses data scarcity and training challenges for visual defect detection in the metal processing industry, but it is incremental as it combines existing generative and contrastive learning techniques.
The paper tackled the problem of insufficient data and inefficient training for industrial surface defect detection by introducing DDPM-MoCo, which uses DDPM to generate high-quality defect samples and MoCo with an enhanced loss for unsupervised training, resulting in an enhanced visual detection method for metal surfaces.
The task of industrial detection based on deep learning often involves solving two problems: (1) obtaining sufficient and effective data samples, (2) and using efficient and convenient model training methods. In this paper, we introduce a novel defect-generation method, named DDPM-MoCo, to address these issues. Firstly, we utilize the Denoising Diffusion Probabilistic Model (DDPM) to generate high-quality defect data samples, overcoming the problem of insufficient sample data for model learning. Furthermore, we utilize the unsupervised learning Momentum Contrast model (MoCo) with an enhanced batch contrastive loss function for training the model on unlabeled data, addressing the efficiency and consistency challenges in large-scale negative sample encoding during diffusion model training. The experimental results showcase an enhanced visual detection method for identifying defects on metal surfaces, covering the entire process, starting from generating unlabeled sample data for training the diffusion model, to utilizing the same labeled sample data for downstream detection tasks. This study offers valuable practical insights and application potential for visual detection in the metal processing industry.