A One-Shot Texture-Perceiving Generative Adversarial Network for Unsupervised Surface Inspection
This addresses the challenge of automated surface inspection in industrial settings where obtaining large annotated datasets is difficult, representing an incremental improvement over prior methods.
The paper tackles the problem of visual surface inspection with limited training data by proposing a hierarchical texture-perceiving GAN that learns from a single normal image in an unsupervised manner, achieving effective defect detection across various datasets.
Visual surface inspection is a challenging task owing to the highly diverse appearance of target surfaces and defective regions. Previous attempts heavily rely on vast quantities of training examples with manual annotation. However, in some practical cases, it is difficult to obtain a large number of samples for inspection. To combat it, we propose a hierarchical texture-perceiving generative adversarial network (HTP-GAN) that is learned from the one-shot normal image in an unsupervised scheme. Specifically, the HTP-GAN contains a pyramid of convolutional GANs that can capture the global structure and fine-grained representation of an image simultaneously. This innovation helps distinguishing defective surface regions from normal ones. In addition, in the discriminator, a texture-perceiving module is devised to capture the spatially invariant representation of normal image via directional convolutions, making it more sensitive to defective areas. Experiments on a variety of datasets consistently demonstrate the effectiveness of our method.