AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

OneFlow: One-class flow for anomaly detection based on a minimal volume region

Łukasz Maziarka, Marek Śmieja, Marcin Sendera, Łukasz Struski, Jacek Tabor, Przemysław Spurek

TPAMI 2021 · Label-efficient and robust learning › OOD and anomaly detection · approach: Anomaly detection with contaminated data · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace log-likelihood loss with minimal-volume Bernstein quantile lossflow model (LL-Flow vs OneFlow) · KDDCUPF1: .6650 -> .9702Improved
replace log-likelihood loss with minimal-volume lossflow model · ThyroidF1: .6989 -> .7634Improved
use OneFlow loss instead of Deep SVDD lossone-class flow · ThyroidF1: .6989 -> .7634Improved
allow non-constant Jacobian (general flow) instead of const-det flow (ablation)OneFlow · ThyroidF1: .7634 -> .7097Hurt
allow non-constant Jacobian (general flow) (ablation)OneFlow · KDDCUPF1: .9702 -> .9712No clear effect
replace NICE backbone with Real-NVP (ablation)OneFlow · MNISTAUC: .964 -> .683Hurt
replace NICE backbone with Glow (ablation)OneFlow · MNISTAUC: .964 -> .895Hurt
replace NICE backbone with Real-NVP (ablation)OneFlow · Fashion-MNISTAUC: .922 -> .769Hurt
replace NICE backbone with Glow (ablation)OneFlow · Fashion-MNISTAUC: .922 -> .775Hurt
use OneFlow instead of LL-Flow for OOD detectionflow model · Fashion-MNIST vs MNIST outliersdetected outliers (%): 89.59% -> 92.47%Improved
use OneFlow instead of LL-Flow for boundary lengthflow model · Doughnut 2Dboundary length: 27.205 -> 7.482Improved
increase alpha from 1% to 10% when training data contain anomalies (ablation)OneFlow · MNIST/Fashion-MNIST with corrupted trainingAUCImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy