Browse SoTA > Computer Vision > Out-of-Distribution Detection

Out-of-Distribution Detection

36 papers with code · Computer Vision

Detect out-of-distribution or anomalous examples.

Benchmarks

Greatest papers with code

Likelihood Ratios for Out-of-Distribution Detection

NeurIPS 2019 google-research/google-research

We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.

OUT-OF-DISTRIBUTION DETECTION

Likelihood Ratios for Out-of-Distribution Detection

NeurIPS 2019 google-research/google-research

We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.

OUT-OF-DISTRIBUTION DETECTION

Deep Anomaly Detection with Outlier Exposure

ICLR 2019 hendrycks/outlier-exposure

We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.

Ranked #2 on Anomaly Detection on CIFAR-10 model detecting CIFAR-10 (using extra training data)

ANOMALY DETECTION OUT-OF-DISTRIBUTION DETECTION

Your classifier is secretly an energy based model and you should treat it like one

ICLR 2020 wgrathwohl/JEM

We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x, y).

OUT-OF-DISTRIBUTION DETECTION

Learning Confidence for Out-of-Distribution Detection in Neural Networks

13 Feb 2018uoguelph-mlrg/confidence_estimation

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong.

OUT-OF-DISTRIBUTION DETECTION

Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification

17 Jan 2020VLL-HD/FrEIA

In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of {\em controlled} information loss allows for an asymptotically exact formulation of the IB, while keeping the INN's generative capabilities intact.

OUT-OF-DISTRIBUTION DETECTION

Flows for simultaneous manifold learning and density estimation

31 Mar 2020johannbrehmer/manifold-flow

We introduce manifold-learning flows (M-flows), a new class of generative models that simultaneously learn the data manifold as well as a tractable probability density on that manifold.

DENOISING DENSITY ESTIMATION DIMENSIONALITY REDUCTION OUT-OF-DISTRIBUTION DETECTION