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 301–310 of 629 papers

TitleStatusHype
Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to TailCode0
Layer Adaptive Deep Neural Networks for Out-of-distribution DetectionCode0
Igeood: An Information Geometry Approach to Out-of-Distribution DetectionCode0
Diffusion Denoising Process for Perceptron Bias in Out-of-distribution DetectionCode0
Identifying Incorrect Classifications with Balanced UncertaintyCode0
Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image ModelsCode0
Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented DialogCode0
Semi-supervised novelty detection using ensembles with regularized disagreementCode0
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution DetectionCode0
LEGO-Learn: Label-Efficient Graph Open-Set LearningCode0
Show:102550
← PrevPage 31 of 63Next →

No leaderboard results yet.