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 91–100 of 629 papers

TitleStatusHype
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized EmbeddingsCode1
The Best of Both Worlds: On the Dilemma of Out-of-distribution DetectionCode1
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language ModelsCode1
Adaptive Label Smoothing for Out-of-Distribution Detection—0
Tensor-Train Point Cloud Compression and Efficient Approximate Nearest-Neighbor Search—0
MetaOOD: Automatic Selection of OOD Detection Models—0
Recent Advances in OOD Detection: Problems and ApproachesCode2
Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening MammogramCode0
Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion Models—0
Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action DetectionCode0
Show:102550
← PrevPage 10 of 63Next →

No leaderboard results yet.