English

PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow

Computer Vision and Pattern Recognition 2023-03-07 v1 Artificial Intelligence

Abstract

During industrial processing, unforeseen defects may arise in products due to uncontrollable factors. Although unsupervised methods have been successful in defect localization, the usual use of pre-trained models results in low-resolution outputs, which damages visual performance. To address this issue, we propose PyramidFlow, the first fully normalizing flow method without pre-trained models that enables high-resolution defect localization. Specifically, we propose a latent template-based defect contrastive localization paradigm to reduce intra-class variance, as the pre-trained models do. In addition, PyramidFlow utilizes pyramid-like normalizing flows for multi-scale fusing and volume normalization to help generalization. Our comprehensive studies on MVTecAD demonstrate the proposed method outperforms the comparable algorithms that do not use external priors, even achieving state-of-the-art performance in more challenging BTAD scenarios.

Keywords

Cite

@article{arxiv.2303.02595,
  title  = {PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow},
  author = {Jiarui Lei and Xiaobo Hu and Yue Wang and Dong Liu},
  journal= {arXiv preprint arXiv:2303.02595},
  year   = {2023}
}

Comments

Accepted to CVPR2023

R2 v1 2026-06-28T09:01:49.215Z