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 551–560 of 629 papers

TitleStatusHype
Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot LearningCode0
EARLIN: Early Out-of-Distribution Detection for Resource-efficient Collaborative Inference—0
Towards Consistent Predictive Confidence through Fitted Ensembles—0
Being a Bit Frequentist Improves Bayesian Neural NetworksCode0
Robust Out-of-Distribution Detection on Deep Probabilistic Generative ModelsCode0
Understanding Softmax Confidence and Uncertainty—0
Detecting Anomalous Event Sequences with Temporal Point Processes—0
Shifting Transformation Learning for Out-of-Distribution Detection—0
Adversarial Self-Supervised Learning for Out-of-Domain DetectionCode0
Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning—0
Show:102550
← PrevPage 56 of 63Next →

No leaderboard results yet.