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 501–525 of 629 papers

TitleStatusHype
Uncertainty-Aware Reliable Text ClassificationCode1
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models—0
Detecting when pre-trained nnU-Net models fail silently for Covid-19 lung lesion segmentation—0
Confidence-based Out-of-Distribution Detection: A Comparative Study and AnalysisCode0
On Out-of-distribution Detection with Energy-based ModelsCode1
On the Practicality of Deterministic Epistemic UncertaintyCode0
Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU—0
EARLIN: Early Out-of-Distribution Detection for Resource-efficient Collaborative Inference—0
Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot LearningCode0
Towards Consistent Predictive Confidence through Fitted Ensembles—0
Out-of-Distribution Detection Using Union of 1-Dimensional SubspacesCode1
Being a Bit Frequentist Improves Bayesian Neural NetworksCode0
A Simple Fix to Mahalanobis Distance for Improving Near-OOD DetectionCode1
Robust Out-of-Distribution Detection on Deep Probabilistic Generative ModelsCode0
InFlow: Robust outlier detection utilizing Normalizing FlowsCode1
Understanding Softmax Confidence and Uncertainty—0
Detecting Anomalous Event Sequences with Temporal Point Processes—0
Provably Robust Detection of Out-of-distribution Data (almost) for freeCode1
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained EnvironmentsCode1
Shifting Transformation Learning for Out-of-Distribution Detection—0
Exploring the Limits of Out-of-Distribution DetectionCode1
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary CodesCode1
Adversarial Self-Supervised Learning for Out-of-Domain DetectionCode0
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive LearningCode1
Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning—0
Show:102550
← PrevPage 21 of 26Next →

No leaderboard results yet.