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 31–40 of 161 papers

TitleStatusHype
Learning Generalized Zero-Shot Learners for Open-Domain Image GeolocalizationCode0
CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned RepresentationCode0
A Gating Model for Bias Calibration in Generalized Zero-shot LearningCode0
Out-Of-Distribution Detection for Audio-visual Generalized Zero-Shot Learning: A General FrameworkCode0
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-ImportanceCode0
Less but Better: Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM SemanticsCode0
Bias-Awareness for Zero-Shot Learning the Seen and UnseenCode0
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the WildCode0
Generalized Zero-Shot Learning Via Over-Complete DistributionCode0
Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)Code0
Show:102550
← PrevPage 4 of 17Next →

No leaderboard results yet.