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 541–550 of 629 papers

TitleStatusHype
Input complexity and out-of-distribution detection with likelihood-based generative modelsCode0
On the Importance of Regularisation & Auxiliary Information in OOD DetectionCode0
On out-of-distribution detection with Bayesian neural networksCode0
Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time ApplicationsCode0
On the Practicality of Deterministic Epistemic UncertaintyCode0
On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution DetectionCode0
Improving Out-of-Distribution Detection by Combining Existing Post-hoc MethodsCode0
Solving Sample-Level Out-of-Distribution Detection on 3D Medical ImagesCode0
SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic SegmentationCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Show:102550
← PrevPage 55 of 63Next →

No leaderboard results yet.