Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Models
This addresses the need for improved OOD detection in machine learning, though it appears incremental as it extends existing likelihood-based approaches to diffusion models.
The paper tackles the problem of Out-of-Distribution detection by proposing a new likelihood ratio method using Denoising Diffusion Probabilistic Models, achieving results comparable to state-of-the-art generative model methods.
Out-of-Distribution detection between dataset pairs has been extensively explored with generative models. We show that likelihood-based Out-of-Distribution detection can be extended to diffusion models by leveraging the fact that they, like other likelihood-based generative models, are dramatically affected by the input sample complexity. Currently, all Out-of-Distribution detection methods with Diffusion Models are reconstruction-based. We propose a new likelihood ratio for Out-of-Distribution detection with Deep Denoising Diffusion Models, which we call the Complexity Corrected Likelihood Ratio. Our likelihood ratio is constructed using Evidence Lower-Bound evaluations from an individual model at various noising levels. We present results that are comparable to state-of-the-art Out-of-Distribution detection methods with generative models.