SOTAVerified

Open Set Learning

Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. Open set learning (OSL) is a more challenging and realistic setting, where there exist test samples from the classes that are unseen during training. Open set recognition (OSR) is the sub-task of detecting test samples which do not come from the training.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 181–190 of 267 papers

TitleStatusHype
Evaluating Uncertainty Calibration for Open-Set Recognition—0
Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training—0
Representation learning with function call graph transformations for malware open set recognition—0
Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces—0
Open-set Recognition via Augmentation-based Similarity Learning—0
PMAL: Open Set Recognition via Robust Prototype Mining—0
openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer—0
Open-Set Recognition of Breast Cancer Treatments—0
Synthetic Unknown Class Learning for Learning Unknowns—0
Latent Cognizance: What Machine Really Learns—0
Show:102550
← PrevPage 19 of 27Next →

No leaderboard results yet.