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 521–530 of 629 papers

TitleStatusHype
Unsupervised Out-of-Distribution Detection by Restoring Lossy Inputs with Variational AutoencoderCode0
SeTAR: Out-of-Distribution Detection with Selective Low-Rank ApproximationCode0
SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class BoundariesCode0
kFolden: k-Fold Ensemble for Out-Of-Distribution DetectionCode0
Key Feature Replacement of In-Distribution Samples for Out-of-Distribution DetectionCode0
BED: Bi-Encoder-Based Detectors for Out-of-Distribution DetectionCode0
Outlier Exposure with Confidence Control for Out-of-Distribution DetectionCode0
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selections and ApproximationsCode0
Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer OutputCode0
Non-Linear Outlier Synthesis for Out-of-Distribution DetectionCode0
Show:102550
← PrevPage 53 of 63Next →

No leaderboard results yet.