Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

By Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn, Bastian Wandt. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2021

329 citations recorded by the source corpus.

In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations. We tackle the problem of automatic defect detection without requiring any image samples of defective parts. Recent works model the distribution of defect-free image data, using either strong statistical priors or overly simplified data representations. In contrast, our approach handles fine-grained representations incorporating the global and local image context while flexibly estimating the density. To this end, we propose a novel fully convolutional cross-scale normalizing flow (CS-Flow) that jointly processes multiple feature maps of different scales. Using normalizing flows to assign meaningful likelihoods to input samples allows for efficient defect detection on image-level. Moreover, due to the preserved spatial arrangement the latent space of the normalizing flow is interpretable which enables to localize defective regions in the image. Our work sets a new state-of-the-art in image-level defect detection on the benchmark datasets Magnetic Tile Defects and MVTec AD showing a 100% AUROC on 4 out of 15 classes.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/5b6b1f438ba40e04a4e3c1e02bd14fe2e66167f9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Onkar Dabeer
  2. Dongqing Zhang
  3. Yang Zou
  4. Latha Pemula
  5. Jongheon Jeong

In Industrial and Manufacturing Engineering

  1. Latha Pemula

Citations in the corpus