Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation

Authors

  • Yuxuan Duan Shanghai Jiao Tong University
  • Yan Hong Shanghai Jiao Tong University
  • Li Niu Shanghai Jiao Tong University
  • Liqing Zhang Shanghai Jiao Tong University

DOI:

https://doi.org/10.1609/aaai.v37i1.25132

Keywords:

CV: Computational Photography, Image & Video Synthesis, ML: Transfer, Domain Adaptation, Multi-Task Learning, ML: Deep Generative Models & Autoencoders

Abstract

The performances of defect inspection have been severely hindered by insufficient defect images in industries, which can be alleviated by generating more samples as data augmentation. We propose the first defect image generation method in the challenging few-shot cases. Given just a handful of defect images and relatively more defect-free ones, our goal is to augment the dataset with new defect images. Our method consists of two training stages. First, we train a data-efficient StyleGAN2 on defect-free images as the backbone. Second, we attach defect-aware residual blocks to the backbone, which learn to produce reasonable defect masks and accordingly manipulate the features within the masked regions by training the added modules on limited defect images. Extensive experiments on MVTec AD dataset not only validate the effectiveness of our method in generating realistic and diverse defect images, but also manifest the benefits it brings to downstream defect inspection tasks. Codes are available at https://github.com/Ldhlwh/DFMGAN.

Downloads

Published

2023-06-26

How to Cite

Duan, Y., Hong, Y., Niu, L., & Zhang, L. (2023). Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 571-578. https://doi.org/10.1609/aaai.v37i1.25132

Issue

Section

AAAI Technical Track on Computer Vision I