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 21–30 of 161 papers

TitleStatusHype
Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning—0
Attribute-Aware Representation Rectification for Generalized Zero-Shot LearningCode0
Dual Feature Augmentation Network for Generalized Zero-shot LearningCode1
Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning—0
Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning—0
Zero-Shot Learning by Harnessing Adversarial SamplesCode0
Improving Zero-Shot Generalization for CLIP with Synthesized PromptsCode1
Synthetic Sample Selection for Generalized Zero-Shot Learning—0
Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot LearningCode1
Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discovery—0
Show:102550
← PrevPage 3 of 17Next →

No leaderboard results yet.