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 41–50 of 629 papers

TitleStatusHype
HALO: Robust Out-of-Distribution Detection via Joint OptimisationCode0
DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories—0
Advancing Out-of-Distribution Detection via Local NeuroplasticityCode0
Enhancing Out-of-Distribution Detection in Medical Imaging with Normalizing FlowsCode0
Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning—0
A Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution DetectionCode0
Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation—0
A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language ModelsCode1
Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution DetectionCode0
Score Combining for Contrastive OOD Detection—0
Show:102550
← PrevPage 5 of 63Next →

No leaderboard results yet.