DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learning

TL;DR

This paper introduces DDPM-MoCo, a combined generative and contrastive learning approach that improves industrial surface defect detection by generating high-quality defect data and efficiently training detection models on unlabeled data.

Contribution

The paper presents a novel method integrating diffusion-based data generation with contrastive learning to enhance defect detection in industrial settings.

Findings

Generated high-quality defect samples using DDPM.

Improved detection accuracy on metal surface defects.

Efficient training on unlabeled data with MoCo.

Abstract

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.