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 271–280 of 629 papers

TitleStatusHype
Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution DetectionCode0
A Hybrid Architecture for Out of Domain Intent Detection and Intent DiscoveryCode1
Improving GAN Training via Feature Space ShrinkageCode1
Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar—0
VRA: Variational Rectified Activation for Out-of-distribution Detection—0
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
Using Semantic Information for Defining and Detecting OOD Inputs—0
Unsupervised Layer-wise Score Aggregation for Textual OOD Detection—0
Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective—0
Uncertainty-Estimation with Normalized Logits for Out-of-Distribution Detection—0
Show:102550
← PrevPage 28 of 63Next →

No leaderboard results yet.