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 361–370 of 629 papers

TitleStatusHype
SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to RankCode0
Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain DetectionCode0
Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and AccuracyCode0
Who Needs Decoders? Efficient Estimation of Sequence-level Attributes—0
A Survey on Out-of-Distribution Detection in NLP—0
Out-of-distribution detection algorithms for robust insect classification—0
Detecting Out-of-distribution Data through In-distribution Class PriorCode0
Open-World Continual Learning: Unifying Novelty Detection and Continual Learning—0
Multidimensional Uncertainty Quantification for Deep Neural Networks—0
Unified Out-Of-Distribution Detection: A Model-Specific Perspective—0
Show:102550
← PrevPage 37 of 63Next →

No leaderboard results yet.