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

Showing 131140 of 161 papers

TitleStatusHype
Generalized Zero- and Few-Shot Learning via Aligned Variational AutoencodersCode0
Mitigating Generation Shifts for Generalized Zero-Shot LearningCode0
Zero-shot Word Sense Disambiguation using Sense Definition EmbeddingsCode0
Online Lifelong Generalized Zero-Shot LearningCode0
Deconstructed Generation-Based Zero-Shot ModelCode0
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-ImportanceCode0
Multi-modal Cycle-consistent Generalized Zero-Shot LearningCode0
Alleviating Feature Confusion for Generative Zero-shot LearningCode0
Generalized Zero- and Few-Shot Learning via Aligned Variational AutoencodersCode0
Evolutionary Generalized Zero-Shot LearningCode0
Show:102550
← PrevPage 14 of 17Next →

No leaderboard results yet.