F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ajith, Varun, Pal, Anindya, Bhattacharya, Saumik, Ghosh, Sayantari
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910964857700352
author Ajith, Varun
Pal, Anindya
Bhattacharya, Saumik
Ghosh, Sayantari
author_facet Ajith, Varun
Pal, Anindya
Bhattacharya, Saumik
Ghosh, Sayantari
contents Nanomaterial research is becoming a vital area for energy, medicine, and materials science, and accurate analysis of the nanoparticle topology is essential to determine their properties. Unfortunately, the lack of high-quality annotated datasets drastically hinders the creation of strong segmentation models for nanoscale imaging. To alleviate this problem, we introduce F-ANcGAN, an attention-enhanced cycle consistent generative adversarial system that can be trained using a limited number of data samples and generates realistic scanning electron microscopy (SEM) images directly from segmentation maps. Our model uses a Style U-Net generator and a U-Net segmentation network equipped with self-attention to capture structural relationships and applies augmentation methods to increase the variety of the dataset. The architecture reached a raw FID score of 17.65 for TiO$_2$ dataset generation, with a further reduction in FID score to nearly 10.39 by using efficient post-processing techniques. By facilitating scalable high-fidelity synthetic dataset generation, our approach can improve the effectiveness of downstream segmentation task training, overcoming severe data shortage issues in nanoparticle analysis, thus extending its applications to resource-limited fields.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles
Ajith, Varun
Pal, Anindya
Bhattacharya, Saumik
Ghosh, Sayantari
Computer Vision and Pattern Recognition
Materials Science
Machine Learning
Image and Video Processing
Nanomaterial research is becoming a vital area for energy, medicine, and materials science, and accurate analysis of the nanoparticle topology is essential to determine their properties. Unfortunately, the lack of high-quality annotated datasets drastically hinders the creation of strong segmentation models for nanoscale imaging. To alleviate this problem, we introduce F-ANcGAN, an attention-enhanced cycle consistent generative adversarial system that can be trained using a limited number of data samples and generates realistic scanning electron microscopy (SEM) images directly from segmentation maps. Our model uses a Style U-Net generator and a U-Net segmentation network equipped with self-attention to capture structural relationships and applies augmentation methods to increase the variety of the dataset. The architecture reached a raw FID score of 17.65 for TiO$_2$ dataset generation, with a further reduction in FID score to nearly 10.39 by using efficient post-processing techniques. By facilitating scalable high-fidelity synthetic dataset generation, our approach can improve the effectiveness of downstream segmentation task training, overcoming severe data shortage issues in nanoparticle analysis, thus extending its applications to resource-limited fields.
title F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles
topic Computer Vision and Pattern Recognition
Materials Science
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2505.18106