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 521–530 of 629 papers

TitleStatusHype
Exploring the Limits of Out-of-Distribution DetectionCode1
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary CodesCode1
Adversarial Self-Supervised Learning for Out-of-Domain DetectionCode0
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive LearningCode1
Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning—0
Can multi-label classification networks know what they don’t know?Code1
Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family DistributionsCode1
MOOD: Multi-level Out-of-distribution DetectionCode1
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection—0
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Show:102550
← PrevPage 53 of 63Next →

No leaderboard results yet.