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 481–490 of 629 papers

TitleStatusHype
Entropic Issues in Likelihood-Based OOD Detection—0
Types of Out-of-Distribution Texts and How to Detect ThemCode1
No True State-of-the-Art? OOD Detection Methods are Inconsistent across DatasetsCode0
On the Impact of Spurious Correlation for Out-of-distribution DetectionCode1
Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPCode1
On the Out-of-distribution Generalization of Probabilistic Image ModellingCode1
NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models—0
kFolden: k-Fold Ensemble for Out-Of-Distribution DetectionCode0
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain DetectionCode0
Semantically Coherent Out-of-Distribution DetectionCode1
Show:102550
← PrevPage 49 of 63Next →

No leaderboard results yet.