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 91–100 of 161 papers

TitleStatusHype
Online Lifelong Generalized Zero-Shot LearningCode0
On Implicit Attribute Localization for Generalized Zero-Shot Learning—0
Task Aligned Generative Meta-learning for Zero-shot Learning—0
Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning—0
Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning—0
Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)Code0
Isometric Propagation Network for Generalized Zero-shot Learning—0
Semantic Borrowing for Generalized Zero-Shot Learning—0
CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition—0
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning—0
Show:102550
← PrevPage 10 of 17Next →

No leaderboard results yet.