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 51–60 of 629 papers

TitleStatusHype
Continual Learning Based on OOD Detection and Task MaskingCode1
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?Code1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic SegmentationCode1
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained EnvironmentsCode1
Beyond AUROC & co. for evaluating out-of-distribution detection performanceCode1
Deep Anomaly Detection with Outlier ExposureCode1
Block Selection Method for Using Feature Norm in Out-of-distribution DetectionCode1
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say NoCode1
A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language ModelsCode1
Show:102550
← PrevPage 6 of 63Next →

No leaderboard results yet.