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 251–267 of 267 papers

TitleStatusHype
Learning the Compositional Spaces for Generalized Zero-shot Learning—0
Distribution Networks for Open Set Learning—0
Query Attack via Opposite-Direction Feature:Towards Robust Image RetrievalCode0
Open Set Learning with Counterfactual Images—0
Collective decision for open set recognition—0
AP18-OLR Challenge: Three Tasks and Their BaselinesCode0
Learning a Neural-network-based Representation for Open Set RecognitionCode0
Recent Advances in Zero-shot Recognition—0
Denoising Autoencoders for Overgeneralization in Neural Networks—0
Adversarial Robustness: Softmax versus Openmax—0
Polyhedral Conic Classifiers for Visual Object Detection and Classification—0
Vocabulary-informed Extreme Value Learning—0
Sparse Representation-based Open Set RecognitionCode0
Specialized Support Vector Machines for Open-set Recognition—0
Semi-supervised Vocabulary-informed Learning—0
Towards Open Set Deep NetworksCode0
Toward an Efficient Multi-class Classification in an Open Universe—0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.