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 31–40 of 629 papers

TitleStatusHype
Background Data Resampling for Outlier-Aware ClassificationCode1
Can multi-label classification networks know what they don’t know?Code1
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say NoCode1
A Simple Fix to Mahalanobis Distance for Improving Near-OOD DetectionCode1
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?Code1
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core QuantitiesCode1
Adversarial vulnerability of powerful near out-of-distribution detectionCode1
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
AdaptiveMix: Improving GAN Training via Feature Space ShrinkageCode1
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution DataCode1
Show:102550
← PrevPage 4 of 63Next →

No leaderboard results yet.