paper-with-me

Papers

Why Normalizing Flows Fail to Detect Out-of-Distribution Data

2020-06-15 · NeurIPS 2020 12 · Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson

Detecting out-of-distribution (OOD) data is crucial for robust machine learning systems. Normalizing flows are flexible deep generative models that often surprisingly fail to distinguish between in- and out-of-distribution data: a flow trained on pictures of clothing assigns higher likelihood to handwritten digits. We investigate why normalizing flows perform poorly for OOD detection. We demonstrate that flows learn local pixel correlations and generic image-to-latent-space transformations which are not specific to the target image dataset. We show that by modifying the architecture of flow coupling layers we can bias the flow towards learning the semantic structure of the target data, improving OOD detection. Our investigation reveals that properties that enable flows to generate high-fidelity images can have a detrimental effect on OOD detection.

📄 PDF Abstract BibTeX arXiv:2006.08545

Code (1)

PolinaKirichenko/flows_ood 공식 구현 pytorch

Tasks

Out 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

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

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

FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detection

2024-06-29 · Rui Cao, Shijie Xue, Jindong Li, Qi Wang 외

Unsupervised graph-level anomaly detection (UGAD) has attracted increasing interest due to its widespread application. In recent studies, knowledge distillation-based methods have been widely used in unsupervised anomaly…

Anomaly DetectionKnowledge DistillationUnsupervised Anomaly Detection

Sliced-Wasserstein normalizing flows: beyond maximum likelihood training

2022-07-12 · Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais

Despite their advantages, normalizing flows generally suffer from several shortcomings including their tendency to generate unrealistic data (e.g., images) and their failing to detect out-of-distribution data. One reason…

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 d…

Density Estimationimage-classificationImage ClassificationOut-of-Distribution Detection+1