SOTAVerified

Out of Distribution (OOD) Detection

Out of Distribution (OOD) Detection is the task of detecting instances that do not belong to the distribution the classifier has been trained on. OOD data is often referred to as "unseen" data, as the model has not encountered it during training.

OOD detection is typically performed by training a model to distinguish between in-distribution (ID) data, which the model has seen during training, and OOD data, which it has not seen. This can be done using a variety of techniques, such as training a separate OOD detector, or modifying the model's architecture or loss function to make it more sensitive to OOD data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 581–590 of 629 papers

TitleStatusHype
The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches—0
Task-agnostic Out-of-Distribution Detection Using Kernel Density EstimationCode0
Density of States Estimation for Out-of-Distribution Detection—0
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-CountsCode1
Why Normalizing Flows Fail to Detect Out-of-Distribution DataCode1
NADS: Neural Architecture Distribution Search for Uncertainty Awareness—0
Entropic Out-of-Distribution Detection: Seamless Detection of Unknown ExamplesCode1
Background Data Resampling for Outlier-Aware ClassificationCode1
Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural NetworksCode0
Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncodersCode1
Show:102550
← PrevPage 59 of 63Next →

No leaderboard results yet.