paper-with-me

Papers

Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations

2025-04-10 · Yifan Ding, Arturas Aleksandrauskas, Amirhossein Ahmadian, Jonas Unger, Fredrik Lindsten, Gabriel Eilertsen

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 $\href{https://github.com/limchaos/Likelihood-OOD.git}{\texttt{https://github.com/limchaos/Likelihood-OOD.git}}$.

📄 PDF Abstract BibTeX arXiv:2504.07793

Code (1)

limchaos/likelihood-ood 공식 구현 pytorch

Tasks

Out-of-Distribution DetectionOut of Distribution (OOD) Detectionvalid

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Back to the Basics: Revisiting Out-of-Distribution Detection Baselines

2022-07-07 · Johnson Kuan, Jonas Mueller

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) Detection

Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

2020-03-06 · NeurIPS 2020 12 · Zhisheng Xiao, Qing Yan, Yali Amit

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) Detection

Gaussian Transforms Modeling and the Estimation of Distributional Regression Functions

2020-11-12 · Richard Spady, Sami Stouli

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…

Econometricsregression

Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows

2026-03-12 · David Baumgartner, Eliezer de Souza da Silva, Iñigo Urteaga arxiv

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 Detection

Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders

2020-03-24 · Gowthami Somepalli, Yexin Wu, Yogesh Balaji, Bhanukiran Vinzamuri 외

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