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 491–500 of 629 papers

TitleStatusHype
Energy-bounded Learning for Robust Models of Code—0
Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning—0
STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data—0
Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models—0
Decomposing Representations for Deterministic Uncertainty Estimation—0
FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection—0
Data Invariants to Understand Unsupervised Out-of-Distribution Detection—0
Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection—0
Out of distribution detection for skin and malaria images—0
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection—0
Show:102550
← PrevPage 50 of 63Next →

No leaderboard results yet.