Out-of-Distribution Detection

170 papers with code • 40 benchmarks • 14 datasets

Detect out-of-distribution or anomalous examples.


Use these libraries to find Out-of-Distribution Detection models and implementations

Efficient Out-of-Distribution Detection of Melanoma with Wavelet-based Normalizing Flows

a-vzer/waveletflowpytorch 9 Aug 2022

In this work, we aim at using these biases with domain-level knowledge of melanoma, to improve likelihood-based OOD detection of malignant images.

09 Aug 2022

FrOoDo: Framework for Out-of-Distribution Detection

meclabtuda/froodo 1 Aug 2022

FrOoDo is an easy-to-use and flexible framework for Out-of-Distribution detection tasks in digital pathology.

01 Aug 2022

XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification

frejberglind/xood 1 Aug 2022

Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning.

01 Aug 2022

Out-of-Distribution Detection with Semantic Mismatch under Masking

cure-lab/moodcat 31 Jul 2022

This paper proposes a novel out-of-distribution (OOD) detection framework named MoodCat for image classifiers.

31 Jul 2022

CODiT: Conformal Out-of-Distribution Detection in Time-Series Data

kaustubhsridhar/time-series-ood 24 Jul 2022

Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution.

24 Jul 2022

Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach

tahabelkhouja/srs 9 Jul 2022

Experiments on diverse real-world benchmarks demonstrate that the SRS method is well-suited for time-series OOD detection when compared to baseline methods.

09 Jul 2022

Out of Distribution Detection via Neural Network Anchoring

rushilanirudh/amp 8 Jul 2022

Heteroscedasticity here refers to the fact that the optimal temperature parameter for each sample can be different, as opposed to conventional approaches that use the same value for the entire distribution.

08 Jul 2022

Back to the Basics: Revisiting Out-of-Distribution Detection Baselines

cleanlab/ood-detection-benchmarks 7 Jul 2022

We study simple methods for out-of-distribution (OOD) image detection that are compatible with any already trained classifier, relying on only its predictions or learned representations.

07 Jul 2022

Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition

amazon-research/long-tailed-ood-detection 4 Jul 2022

However, in real-world applications, it is common for the training sets to have long-tailed distributions.

04 Jul 2022