InFlow: Robust outlier detection utilizing Normalizing Flows
Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while detecting Out-of-Distribution (OOD) inputs as they directly encode the local features of the input representations in their latent space. In this paper, we solve this overconfidence issue of normalizing flows by demonstrating that flows, if extended by an attention mechanism, can reliably detect outliers including adversarial attacks. Our approach does not require outlier data for training and we showcase the efficiency of our method for OOD detection by reporting state-of-the-art performance in diverse experimental settings. Code available at https://github.com/ComputationalRadiationPhysics/InFlow .
Code (1)
Tasks
Density EstimationOutlier DetectionOut of Distribution (OOD) DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data
Detecting test data deviating from training data is a central problem for safe and robust machine learning. Likelihoods learned by a generative model, e.g., a normalizing flow via standard log-likelihood training, perfor…
Anomaly DetectionOutlier DetectionQuantum Normalizing Flows for Anomaly Detection
A Normalizing Flow computes a bijective mapping from an arbitrary distribution to a predefined (e.g. normal) distribution. Such a flow can be used to address different tasks, e.g. anomaly detection, once such a mapping h…
Anomaly DetectionNormalizing flows for novelty detection in industrial time series data
Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score u…
Anomaly DetectionNovelty DetectionTime SeriesTime Series AnalysisOptimal Reservoir Operations using Long Short-Term Memory Network
A reliable forecast of inflows to the reservoir is a key factor in the optimal operation of reservoirs. Real-time operation of the reservoir based on forecasts of inflows can lead to substantial economic gains. However, …
Anomaly Detectioni-flow: High-dimensional Integration and Sampling with Normalizing Flows
In many fields of science, high-dimensional integration is required. Numerical methods have been developed to evaluate these complex integrals. We introduce the code i-flow, a python package that performs high-dimensiona…
Numerical IntegrationVocal Bursts Intensity Prediction