paper-with-me

Papers

InFlow: Robust outlier detection utilizing Normalizing Flows

2021-06-10 · Nishant Kumar, Pia Hanfeld, Michael Hecht, Michael Bussmann, Stefan Gumhold, Nico Hoffmann

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 .

📄 PDF Abstract BibTeX arXiv:2106.12894

Code (1)

ComputationalRadiationPhysics/InFlow 공식 구현 pytorch

Tasks

Density EstimationOutlier DetectionOut of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data

2022-08-30 · Robert Schmier, Ullrich Köthe, Christoph-Nikolas Straehle

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 Detection

Quantum Normalizing Flows for Anomaly Detection

2024-02-05 · Bodo Rosenhahn, Christoph Hirche

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 Detection

Normalizing flows for novelty detection in industrial time series data

2019-06-17 · Maximilian Schmidt, Marko Simic

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 Analysis

Optimal Reservoir Operations using Long Short-Term Memory Network

2021-09-07 · Asha Devi Singh, Anurag Singh

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 Detection

i-flow: High-dimensional Integration and Sampling with Normalizing Flows

2020-01-15 · Christina Gao, Joshua Isaacson, Claudius Krause

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