FFGAN: Feature Fusion GAN for Few-shot Image Classification

Runzhou Hua, Ji Zhang*, Jingfeng Xue, Yong Wang, Zhenyan Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the rapid development and wide application of deep learning in large-scale data training models, the problem of insufficient data has become a constraint on the performance and applicability of deep learning models. In response to this issue, researchers have proposed methods based on feature fusion. However, existing feature fusion methods have certain limitations in terms of generating diverse and accurate images. To further improve the effectiveness of image classification tasks, this paper proposes a novel method for few-shot image generation based on local feature fusion. This method combines the concepts of Feature Fusion and Generative Adversarial Networks (FFGAN) to improve the quality and diversity of generated images. It addresses issues such as spatial misalignment in generated images. Additionally, this paper introduces a local reconstruction loss to optimize the local feature fusion module. The local reconstruction loss improves the quality of few-shot image generation by enforcing the generated images to closely resemble the corresponding local positions of input images in certain local regions. Finally, extensive experiments are conducted in image generation, image classification and image visualization.

Original languageEnglish
Title of host publicationProceedings - 2024 Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages96-102
Number of pages7
ISBN (Electronic)9798350374407
DOIs
Publication statusPublished - 2024
Event5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024 - Dalian, China
Duration: 12 Apr 202414 Apr 2024

Publication series

NameProceedings - 2024 Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024

Conference

Conference5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024
Country/TerritoryChina
CityDalian
Period12/04/2414/04/24

Keywords

  • feature fusion
  • few-shot image generation
  • generative adversarial networks
  • local reconstruction loss

Fingerprint

Dive into the research topics of 'FFGAN: Feature Fusion GAN for Few-shot Image Classification'. Together they form a unique fingerprint.

Cite this