A step-by-step training method for multi generator GANs with application to anomaly detection and cybersecurity

Adiban, Mohammad; Siniscalchi, Sabato Marco; Salvi, Giampiero

doi:10.1016/j.neucom.2023.03.056

Cited by 16 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anomaly detection [1] is the process of identifying image data that significantly deviates from typical instances. Currently, the scope of anomaly detection encompasses a variety of applications, including defect detection [2], medical diagnosis [3] [4], video surveillance [5] [6], financial transaction monitoring [7], and network security [8]. Of particular note, anomaly detection finds extensive utility within the industrial sector, spanning applications such as detecting conductive particles in glass chips [9] and inspecting steel surfaces [10].…”

Section: Introductionmentioning

confidence: 99%

SCGAN: Extract Features From Normal Semantics for Unsupervised Anomaly Detection

Dai,

Zhang,

Fan

et al. 2023

IEEE Access

View full text Add to dashboard Cite

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 involves a Semantic CopyPaste based Generative Adversarial Network (SCGAN) for unsupervised anomaly detection. To enable the comprehensive acquisition of semantic features within intricate real-world images, we embrace an encoder-decoder-encoder as the fundamental network structure. In practical terms, our approach commences with the input image being subjected to the CopyPaste augmentation module. Here, we strategically copy N patches, each constituting 1% of the image's area, from normal samples. These patches are then randomly pasted into different regions of the original image. Subsequently, a generative adversarial network is trained to facilitate sample reconstruction. A noteworthy augmentation to the network's channel attention capabilities entails the incorporation of a multi-scale channel attention module within the first encoder. This module serves to emphasize contextual features across varying scales within the image. During the test, we detect anomalous regions by meticulously comparing residuals between the input image and its reconstructed counterpart. Our methodology is rigorously validated through diverse experiments conducted on challenging MVTec and BTAD public datasets. The results conclusively affirm the state-of-the-art performance achieved by our proposed method in the domain of anomaly detection.

show abstract