MFF: Multi-modal feature fusion for zero-shot learning

Cao, Weipeng; Wu, Yuhao; Huang, Chengchao; Patwary, Muhammed J. A.; Wang, Xizhao

doi:10.1016/j.neucom.2022.09.070

Cited by 18 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to balance the stability and high quality of generated samples, many improved methods have been proposed. F-VAEGAN-D2 [11] and MFF [12] model, which comprehensively utilizing the advantages of GAN and VAE, combines the CVAE model with semantic attributes as conditions and the CGAN model with category attributes as conditions to generate high-quality visual features for invisible classes…”

Section: Zero-shot Learning Based On Generative Modelmentioning

confidence: 99%

Research on Zero-Shot Learning Based on Generative Model

Yan,

Zeng,

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Zero-shot learning is mainly applied in image classification tasks. Traditional classification methods use a large number of manually labeled data samples, which is time-consuming and inefficient. Zero-shot learning use semantic information to recognizes unknown images in the absence of labeled training data, saving labor costs. The mainstream method of early zero-shot learning, which only used known class data during training, was susceptible to domain drift and pivot point issues during testing, resulting in a decrease in model performance on the test set. In recent years, researchers have begun to use the generative model to solve the above problems. By generating the sample features of unknown classes to make up for the lack of visual data of unknown classes in training, the problem of imbalance between known and unknown class data has been alleviated. Firstly, introducing the concept of zero-shot learning briefly. Secondly, it briefly introduces traditional zero-shot learning and generalized zero-shot learning. Thirdly, two kinds of zero-shot learning methods based on the generative model are emphatically introduced. Then, the datasets and evaluation methods of zero-shot learning are briefly introduced, and the experimental results of the classical model are compared and analyzed. Finally, make a summary and outlook.

show abstract

Section: Zero-shot Learning Based On Generative Modelmentioning

confidence: 99%

Research on Zero-Shot Learning Based on Generative Model

Yan,

Zeng,

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

A review on multimodal zero‐shot learning

Cao

Sun

et al. 2023

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

Multimodal learning provides a path to fully utilize all types of information related to the modeling target to provide the model with a global vision. Zero-shot learning (ZSL) is a general solution for incorporating prior knowledge into data-driven models and achieving accurate class identification. The combination of the two, known as multimodal ZSL (MZSL), can fully exploit the advantages of both technologies and is expected to produce models with greater generalization ability. However, the MZSL algorithms and applicationshave not yet been thoroughly investigated and summarized. This study fills this gap by providing an objective overview of MZSL's definition, typical algorithms, representative applications, and critical issues. This article will not only provide researchers in this field with a comprehensive perspective, but it will also highlight several promising research directions.

show abstract

MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Chen

Jiang

et al. 2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

MFF: Multi-modal feature fusion for zero-shot learning

Cited by 18 publications

References 10 publications

Research on Zero-Shot Learning Based on Generative Model

Research on Zero-Shot Learning Based on Generative Model

A review on multimodal zero‐shot learning

MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Contact Info

Product

Resources

About