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 391–400 of 629 papers

TitleStatusHype
Out-of-Distribution Detection with Class Ratio Estimation—0
What do we learn? Debunking the Myth of Unsupervised Outlier Detection—0
Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)Code1
Transformer-based out-of-distribution detection for clinically safe segmentationCode0
How Useful are Gradients for OOD Detection Really?—0
Robust Representation via Dynamic Feature AggregationCode0
KNN-Contrastive Learning for Out-of-Domain Intent Classification—0
Evaluating the Practical Utility of Confidence-score based Techniques for Unsupervised Open-world Classification—0
Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution DetectionCode0
Metric Learning and Adaptive Boundary for Out-of-Domain DetectionCode0
Show:102550
← PrevPage 40 of 63Next →

No leaderboard results yet.