SCGAN: Extract Features From Normal Semantics for Unsupervised Anomaly Detection

SCGAN: Extract Features From Normal Semantics for Unsupervised Anomaly Detection

Anomaly detection within the realm of industrial products seeks to identify regions of image semantics that deviate from established normal patterns. Given the inherent challenges associated with collecting anomaly samples, we exclusively extract features from normal semantics. Our proposed solution...

Full description

Bibliographic Details
Main Authors: Yang Dai, Lin Zhang, Fu-You Fan, Ya-Juan Wu, Ze-Kuan Zhao
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Anomaly detection
generative adversarial networks
channel attention
multi-scale channel attention module
Online Access:https://ieeexplore.ieee.org/document/10345606/

Internet

https://ieeexplore.ieee.org/document/10345606/

Similar Items