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 41–50 of 161 papers

TitleStatusHype
Recognition of Unseen Bird Species by Learning from Field GuidesCode0
Learn to Adapt for Generalized Zero-Shot Text ClassificationCode1
Zero-Shot Logit AdjustmentCode1
Deconstructed Generation-Based Zero-Shot ModelCode0
Interpretable Saliency Maps And Self-Supervised Learning For Generalized Zero Shot Medical Image Classification—0
Unseen Classes at a Later Time? No ProblemCode1
Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector—0
Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis—0
A Gating Model for Bias Calibration in Generalized Zero-shot LearningCode0
Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning—0
Show:102550
← PrevPage 5 of 17Next →

No leaderboard results yet.