Multi-Label Zero-Shot Learning With Adversarial and Variational Techniques

Multi-label zero-shot learning expands upon the traditional single-label zero-shot learning paradigm by addressing the challenge of accurately classifying images containing multiple unseen classes, which are not part of the training data. Current techniques rely on attention mechanisms to tackle the...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Muqaddas Gull, Omar Arif
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2024-01-01
Saila:	IEEE Access
Gaiak:	Conditional variational autoencoder conditional generative adversarial network generalized zero-shot learning regressor zero-shot learning
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/10589634/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!