SOTAVerified

Generalized Zero-Shot Learning

In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 161 papers

TitleStatusHype
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the WildCode0
Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)Code0
Dual Expert Distillation Network for Generalized Zero-Shot LearningCode0
Unifying Unsupervised Domain Adaptation and Zero-Shot Visual RecognitionCode0
Learning Generalized Zero-Shot Learners for Open-Domain Image GeolocalizationCode0
Bias-Awareness for Zero-Shot Learning the Seen and UnseenCode0
Out-Of-Distribution Detection for Audio-visual Generalized Zero-Shot Learning: A General FrameworkCode0
On the Transferability of Visual Features in Generalized Zero-Shot LearningCode0
A Review of Open-World Learning and Steps Toward Open-World Learning Without LabelsCode0
Attribute-Aware Representation Rectification for Generalized Zero-Shot LearningCode0
Show:102550
← PrevPage 15 of 17Next →

No leaderboard results yet.