Density of States Estimation for Out-of-Distribution Detection

06/16/2020
by   Warren R. Morningstar, et al.
0

Perhaps surprisingly, recent studies have shown probabilistic model likelihoods have poor specificity for out-of-distribution (OOD) detection and often assign higher likelihoods to OOD data than in-distribution data. To ameliorate this issue we propose DoSE, the density of states estimator. Drawing on the statistical physics notion of “density of states,” the DoSE decision rule avoids direct comparison of model probabilities, and instead utilizes the “probability of the model probability,” or indeed the frequency of any reasonable statistic. The frequency is calculated using nonparametric density estimators (e.g., KDE and one-class SVM) which measure the typicality of various model statistics given the training data and from which we can flag test points with low typicality as anomalous. Unlike many other methods, DoSE requires neither labeled data nor OOD examples. DoSE is modular and can be trivially applied to any existing, trained model. We demonstrate DoSE's state-of-the-art performance against other unsupervised OOD detectors on previously established “hard” benchmarks.

READ FULL TEXT
research
02/24/2021

Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning

Purpose: We propose a general framework for quantifying predictive uncer...
research
07/19/2020

Kernel Assisted Learning for Personalized Dose Finding

An individualized dose rule recommends a dose level within a continuous ...
research
09/22/2021

Adaptive Contrast Test for Dose-Response Studies and Modeling

We propose a powerful adaptive contrast test with ordinal constraint con...
research
06/13/2023

An Approach to Nonparametric Inference on the Causal Dose Response Function

The causal dose response curve is commonly selected as the statistical p...
research
04/12/2023

A Multi-Arm Two-Stage (MATS) Design for Proof-of-Concept and Dose Optimization in Early-Phase Oncology Trials

The Project Optimus initiative by the FDA's Oncology Center of Excellenc...
research
02/16/2021

Hierarchical VAEs Know What They Don't Know

Deep generative models have shown themselves to be state-of-the-art dens...
research
05/23/2018

Deep Learning Estimation of Absorbed Dose for Nuclear Medicine Diagnostics

The distribution of energy dose from Lu^177 radiotherapy can be estimate...

Please sign up or login with your details

Forgot password? Click here to reset