paper-with-me

Papers

Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows

2024-02-09 · Evan D. Cook, Marc-Antoine Lavoie, Steven L. Waslander

Out-of-distribution (OOD) detection is a critical task for safe deployment of learning systems in the open world setting. In this work, we investigate the use of feature density estimation via normalizing flows for OOD detection and present a fully unsupervised approach which requires no exposure to OOD data, avoiding researcher bias in OOD sample selection. This is a post-hoc method which can be applied to any pretrained model, and involves training a lightweight auxiliary normalizing flow model to perform the out-of-distribution detection via density thresholding. Experiments on OOD detection in image classification show strong results for far-OOD data detection with only a single epoch of flow training, including 98.2% AUROC for ImageNet-1k vs. Textures, which exceeds the state of the art by 7.8%. We additionally explore the connection between the feature space distribution of the pretrained model and the performance of our method. Finally, we provide insights into training pitfalls that have plagued normalizing flows for use in OOD detection.

📄 PDF Abstract BibTeX arXiv:2402.06537

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimationimage-classificationImage ClassificationOut-of-Distribution 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

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

2022-02-16 · ICLR 2022 4 · Enyan Dai, Jie Chen

Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks. Detecting anomali…

Anomaly DetectionDensity EstimationTime SeriesTime Series Analysis+1

Anomaly Detection in Trajectory Data with Normalizing Flows

2020-04-13 · Madson L. D. Dias, César Lincoln C. Mattos, Ticiana L. C. da Silva, José Antônio F. de Macedo 외

The task of detecting anomalous data patterns is as important in practical applications as challenging. In the context of spatial data, recognition of unexpected trajectories brings additional difficulties, such as high …

Anomaly DetectionDensity Estimation

Out-of-distribution detection using normalizing flows on the data manifold

2023-08-26 · Seyedeh Fatemeh Razavi, Mohammad Mahdi Mehmanchi, Reshad Hosseini, Mostafa Tavassolipour

Using the intuition that out-of-distribution data have lower likelihoods, a common approach for out-of-distribution detection involves estimating the underlying data distribution. Normalizing flows are likelihood-based g…

Density EstimationOut-of-Distribution Detection

InFlow: Robust outlier detection utilizing Normalizing Flows

2021-06-10 · Nishant Kumar, Pia Hanfeld, Michael Hecht, Michael Bussmann 외

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) inp…

Density EstimationOutlier DetectionOut of Distribution (OOD) Detection

Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning

2023-11-11 · Jianxiang Feng, JongSeok Lee, Simon Geisler, Stephan Gunnemann 외

To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required. A powerful approach for OOD detection is based on density estimation with No…

2D Object DetectionDensity Estimationobject-detectionObject Detection+2