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 191–200 of 267 papers

TitleStatusHype
Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks—0
Distance-Based Background Class Regularization for Open-Set Recognition—0
Generalizing Cross Entropy Loss with a Beta Proper Composite Loss: An Improved Loss Function for Open Set Recognition—0
A novel network training approach for open set image recognition—0
Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition—0
An Adaptable Deep Learning-Based Intrusion Detection System to Zero-Day Attacks—0
A Survey on Open Set Recognition—0
M2IOSR: Maximal Mutual Information Open Set Recognition—0
Reconstruction guided Meta-learning for Few Shot Open Set Recognition—0
Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial NetworksCode0
Show:102550
← PrevPage 20 of 27Next →

No leaderboard results yet.