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 71–80 of 161 papers

TitleStatusHype
Rectification-based Knowledge Retention for Continual Learning—0
Contrastive Embedding for Generalized Zero-Shot LearningCode1
A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings—0
Learning without Seeing nor Knowing: Towards Open Zero-Shot Learning—0
Online Lifelong Generalized Zero-Shot LearningCode0
DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning—0
On Implicit Attribute Localization for Generalized Zero-Shot Learning—0
Goal-Oriented Gaze Estimation for Zero-Shot LearningCode1
Task Aligned Generative Meta-learning for Zero-shot Learning—0
Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning—0
Show:102550
← PrevPage 8 of 17Next →

No leaderboard results yet.