Semantic Mask Reconstruction and Category Semantic Learning for few-shot image generation
Neural Networks · 2025
DOI: 10.1016/j.neunet.2024.106946 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Networks, 2025. Verfasst von Ting Xiao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, 200237, China; Departmen…. Hauptthemen laut MEDLINE: Semantics, Image Processing, Computer-Assisted, Neural Networks, Computer, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Key Technologies Research and Development Program, National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Few-shot image generation aims at generating novel images for the unseen category when given K images from the same category. Despite significant advancements in existing few-shot image generation methods, great challenges remain regarding the quality and diversity of the generated images. This issue stems from the model's struggle to fully comprehend the semantic content of images and extract sufficiently semantic representations. To address these issues, we propose a semantic mask reconstruction (SMR) and category semantic learning (CSL) method for few-shot image generation. Specifically, SMR performs mask reconstruction in a high-level semantic space and designs a strategy for dynamically adjusting the mask ratio, which increases the difficulty of the generation tasks by gradually increasing the mask ratio to enhance the learning ability of the discriminator, thereby prompting the generator to learn more critical features relevant to the generation task. In addition, CSL introduces a triplet loss to optimize the distance between the generated image, its corresponding input image, and input images of other categories. This encourages the generative model to discern subtle differences between categories, thereby achieving more fine-grained generation and improving the fidelity of generated images. Both SMR and CSL can function as plug-and-play modules. Extensive experimental results across three standard datasets demonstrate that the SMR-CSL outperforms other methods in terms of the quality and diversity of the generated images. Furthermore, the results of downstream classification experiments verify that the images generated by the proposed method can effectively assist downstream classification tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, 200237, China; Department of Computer Science and Engineering, East China University of Scienc…
- Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China. Electronic address: y30231031@mail.ecust.edu.cn.
- Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China. Electronic address: y80210029@mail.ecust.edu.cn.
Förderung
- Key Technologies Research and Development Program
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Xiao, T., Cai, Y., Guan, J., & Wang, Z. (2025). Semantic Mask Reconstruction and Category Semantic Learning for few-shot image generation. Neural Networks. https://doi.org/10.1016/j.neunet.2024.106946
Vancouver
Xiao T, Cai Y, Guan J, Wang Z. Semantic Mask Reconstruction and Category Semantic Learning for few-shot image generation. Neural Networks. 2025. doi:10.1016/j.neunet.2024.106946
BibTeX
@article{Xiao2025,
author = {Xiao, Ting and Cai, Yunjie and Guan, Jiaoyan and Wang, Zhe},
title = {Semantic Mask Reconstruction and Category Semantic Learning for few-shot image generation},
journal = {Neural Networks},
year = {2025},
doi = {10.1016/j.neunet.2024.106946}
}
EUVIMED