Enhancing Semantic-Consistent Features and Transforming Discriminative Features for Generalized Zero-Shot Classifications
Generalized zero-shot learning (GZSL) aims to classify classes that do not appear during training. Recent state-of-the-art approaches rely on generative models, which use correlating semantic embeddings to synthesize unseen classes visual features; however, these approaches ignore the semantic and v...
Main Authors: | Guan Yang, Ayou Han, Xiaoming Liu, Yang Liu, Tao Wei, Zhiyuan Zhang |
---|---|
格式: | 文件 |
语言: | English |
出版: |
MDPI AG
2022-12-01
|
丛编: | Applied Sciences |
主题: | |
在线阅读: | https://www.mdpi.com/2076-3417/12/24/12642 |
相似书籍
-
Semantic Space Analysis for Zero-Shot Learning on SAR Images
由: Bo Liu, et al.
出版: (2024-07-01) -
Hand and Pose-Based Feature Selection for Zero-Shot Sign Language Recognition
由: Giray Sercan Ozcan, et al.
出版: (2024-01-01) -
Zero-shot intelligent fault diagnosis via semantic fusion embedding
由: Honghua Xu, et al.
出版: (2025-01-01) -
Zero-Shot Image Classification Algorithm Based on Particle Swarm Optimization Fusion Feature
出版: (2019-12-01) -
Zero-shot learning via visual-semantic aligned autoencoder
由: Tianshu Wei, et al.
出版: (2023-06-01)