Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection
원문 초록
In this paper, we propose the Adversarial Denoising Diffusion Model (ADDM). The ADDM is based on the Denoising Diffusion Probabilistic Model (DDPM) but complementarily trained by adversarial learning. The proposed adversarial learning is achieved by classifying model-based denoised samples and samples to which random Gaussian noise is added to a specific sampling step. With the addition of explicit adversarial learning on data samples, ADDM can learn the semantic characteristics of the data more robustly during training, which achieves a similar data sampling performance with much fewer sampling steps than DDPM. We apply ADDM to anomaly detection in unsupervised MRI images. Experimental results show that the proposed ADDM outperformed existing generative model-based unsupervised anomaly detection methods. In particular, compared to other DDPM-based anomaly detection methods, the proposed ADDM shows better performance with the same number of sampling steps and similar performance with 50% fewer sampling steps.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Shell Theory: A Statistical Model of Reality
DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection
Fast Unsupervised Anomaly Detection in Traffic Videos
Learning Neural Representations for Network Anomaly Detection
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention
토론
이 논문과 연결된 포럼 글이 아직 없습니다.