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
Generalized Zero-Shot Learning Via Over-Complete DistributionCode0
Generalized Zero- and Few-Shot Learning via Aligned Variational AutoencodersCode0
Learning Generalized Zero-Shot Learners for Open-Domain Image GeolocalizationCode0
Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning—0
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning—0
From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process—0
A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition—0
CLAREL: Classification via retrieval loss for zero-shot learning—0
Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention—0
Fine-grained Event Classification in News-like Text Snippets - Shared Task 2, CASE 2021—0
Show:102550
← PrevPage 7 of 17Next →

No leaderboard results yet.