Anomaly detection using Diffusion-based methods
This work addresses anomaly detection problems for data scientists and practitioners, but it appears incremental as it applies existing diffusion methods to a new application area.
This paper tackles anomaly detection by evaluating diffusion-based models like DDPMs and DiTs against traditional methods, finding they offer superior adaptability, scalability, and robustness for complex real-world tasks.
This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets. Diffusion-based architectures, including Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs), are evaluated for their performance using reconstruction objectives. By leveraging the strengths of these models, this study benchmarks their performance against traditional anomaly detection methods such as Isolation Forests, One-Class SVMs, and COPOD. The results demonstrate the superior adaptability, scalability, and robustness of diffusion-based methods in handling complex real-world anomaly detection tasks. Key findings highlight the role of reconstruction error in enhancing detection accuracy and underscore the scalability of these models to high-dimensional datasets. Future directions include optimizing encoder-decoder architectures and exploring multi-modal datasets to further advance diffusion-based anomaly detection.