Zero-Shot Image Classification Method Based on Attention Mechanism and Semantic Information Fusion

Zero-Shot Image Classification Method Based on Attention Mechanism and Semantic Information Fusion

The zero-shot image classification (ZSIC) is designed to solve the classification problem when the sample is very small, or the category is missing. A common method is to use attribute or word vectors as a priori category features (auxiliary information) and complete the domain transfer from trainin...

Full description

Bibliographic Details
Main Authors: Yaru Wang, Lilong Feng, Xiaoke Song, Dawei Xu, Yongjie Zhai
Format: Article
Language:English
Published: MDPI AG 2023-02-01
Series:Sensors
Subjects:
image classification
attention mechanism
matrix decomposition
attributes
word vectors
Online Access:https://www.mdpi.com/1424-8220/23/4/2311

Internet

https://www.mdpi.com/1424-8220/23/4/2311

Similar Items