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 511–520 of 629 papers

TitleStatusHype
Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty—0
On out-of-distribution detection with Bayesian neural networksCode0
Gated Information Bottleneck for Generalization in Sequential EnvironmentsCode0
Out-of-Distribution Detection for Medical Applications: Guidelines for Practical EvaluationCode0
Revisiting flow generative models for Out-of-distribution detection—0
Decomposing Texture and Semantics for Out-of-distribution Detection—0
Towards Unknown-aware Learning with Virtual Outlier Synthesis—0
Towards Unknown-aware Deep Q-Learning—0
MOG: Molecular Out-of-distribution Generation with Energy-based Models—0
Efficient Out-of-Distribution Detection via CVAE data Generation—0
Show:102550
← PrevPage 52 of 63Next →

No leaderboard results yet.