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 561–570 of 629 papers

TitleStatusHype
A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space—0
OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification—0
Feature Space Singularity for Out-of-Distribution DetectionCode1
Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment—0
Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular DataCode1
Out-of-distribution detection for regression tasks: parameter versus predictor entropy—0
Uncertainty Aware Semi-Supervised Learning on Graph DataCode1
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution DataCode1
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution ExamplesCode0
Learn what you can't learn: Regularized Ensembles for Transductive out-of-distribution detection—0
Show:102550
← PrevPage 57 of 63Next →

No leaderboard results yet.