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...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Muqaddas Gull, Omar Arif
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2024-01-01
Serija:	IEEE Access
Teme:	Conditional variational autoencoder conditional generative adversarial network generalized zero-shot learning regressor zero-shot learning
Online dostop:	https://ieeexplore.ieee.org/document/10589634/
Oznake:	Označite Brez oznak, prvi označite!