Learning MLatent Representations for Generalized Zero-Shot Learning

In generative adversarial network (GAN) based zero-shot learning (ZSL) approaches, the synthesized unseen visual features are inevitably prone to seen classes since the feature generator is merely trained on seen references, which causes the inconsistency between visual features and their correspond...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on multimedia 2023, Vol.25, p.2252-2265
Hauptverfasser:	Ye, Yalan, Pan, Tongjie, Luo, Tonghoujun, Li, Jingjing, Shen, Heng Tao
Format:	Artikel
Sprache:	eng
Schlagworte:	Cows Embedding Generative adversarial network Generative adversarial networks Image color analysis latent representations Mutual information Representations semantic-irrelevant semantic-relevant Semantics Task analysis Visualization Zero-shot learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!