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 61–70 of 161 papers

TitleStatusHype
A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning—0
Improving Generalized Zero-Shot Learning by Semantic Discriminator—0
Adaptive Confidence Smoothing for Generalized Zero-Shot Learning—0
Audio-visual Generalized Zero-shot Learning the Easy Way—0
Global Semantic Consistency for Zero-Shot Learning—0
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning—0
Distinguishing Unseen From Seen for Generalized Zero-Shot Learning—0
Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning—0
DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning—0
A Generative Approach to Zero-Shot and Few-Shot Action Recognition—0
Show:102550
← PrevPage 7 of 17Next →

No leaderboard results yet.