Research and application of an improved Skip-GANomaly detection model
Yefeng Liu, Hanlin Sun, Yihang Ma · 2024
Generative adversarial network (GAN) has low discrimination ability for abnormal samples or noise data in anomaly detection tasks, which affects the detection effect. This paper proposes an improved model based on Skip-GANomaly network, which adds a Self-Attention module to the encoder of the generator to improve the model's ability to capture long-distance dependence of input data, so as to better understand the overall structure and local details of the image. And dynamically focus on the most important parts of the anomaly detection task, such as the shape, texture, color of the object, so that the accuracy of the model is significantly improved. KolektorSDD dataset was used for experimental verification. The results show that compared with AnoGAN, GANomaly, and Skip-GANomaly, the proposed model has better performance in Receiver Operating Characteristic (Receiver Operating Characteristic, receiver operating characteristic, receiver operating characteristic). the performance of the proposed model in terms of the Area Under the Curve (AUC) is better, which proves the effectiveness of the model and has a certain application prospect.