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 141–150 of 267 papers

TitleStatusHype
On the link between generative semi-supervised learning and generative open-set recognition—0
M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios—0
Open-World Object Detection via Discriminative Class Prototype Learning—0
Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discovery—0
Improving Open-Set Semi-Supervised Learning with Self-SupervisionCode0
Contracting Skeletal Kinematics for Human-Related Video Anomaly DetectionCode0
Subject-Independent Brain-Computer Interfaces with Open-Set Subject Recognition—0
Vocabulary-informed Zero-shot and Open-set LearningCode0
Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization—0
FedPD: Federated Open Set Recognition with Parameter Disentanglement—0
Show:102550
← PrevPage 15 of 27Next →

No leaderboard results yet.