Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning systems, particularly in safety-critical applications. Likelihood-based deep generative models have historically faced criticism for their unsatisfactory performance in OOD detection, often assigning higher likelihood to OOD data than in-distribution samples when applied to image data. In this work, we demonstrate that likelihood is not inherently flawed. Rather, several properties in the images space prohibit likelihood as a valid detection score. Given a sufficiently good likelihood estimator, specifically using the probability flow formulation of a diffusion model, we show that likelihood-based methods can still perform on par with state-of-the-art methods when applied in the representation space of pre-trained encoders. The code of our work can be found at $\href{https://github.com/limchaos/Likelihood-OOD.git}{\texttt{https://github.com/limchaos/Likelihood-OOD.git}}$.
Code (1)
Tasks
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionvalidMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Back to the Basics: Revisiting Out-of-Distribution Detection Baselines
We study simple methods for out-of-distribution (OOD) image detection that are compatible with any already trained classifier, relying on only its predictions or learned representations. Evaluating the OOD detection perf…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionLikelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by set…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionGaussian Transforms Modeling and the Estimation of Distributional Regression Functions
We propose flexible Gaussian representations for conditional cumulative distribution functions and give a concave likelihood criterion for their estimation. Optimal representations satisfy the monotonicity property of co…
EconometricsregressionAnomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
Deep generative models for anomaly detection in multivariate time-series are typically trained by maximizing observed data likelihood. However, likelihood in observation space measures marginal density rather than confor…
Anomaly DetectionUnsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications. Deep generative modeling has emerged as a dominant paradigm to model complex data distributions without labels.…
Anomaly DetectionOut of Distribution (OOD) DetectionRepresentation LearningUnsupervised Anomaly Detection