Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy

2024/02/28 by Bashir Kazimi, Kazimi, Bashir, Karina Ruzaeva +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Materials Science · #Advanced Electron Microscopy Techniques and Applications #Electron and X-Ray Spectroscopy Techniques

paper · pdf · doi:10.48550/arxiv.2402.18286

Abstract

In this work, we explore the potential of self-supervised learning with Generative Adversarial Networks (GANs) for electron microscopy datasets. We show how self-supervised pretraining facilitates efficient fine-tuning for a spectrum of downstream tasks, including semantic segmentation, denoising, noise & background removal, and super-resolution. Experimentation with varying model complexities and receptive field sizes reveals the remarkable phenomenon that fine-tuned models of lower complexity consistently outperform more complex models with random weight initialization. We demonstrate the versatility of self-supervised pretraining across various downstream tasks in the context of electron microscopy, allowing faster convergence and better performance. We conclude that self-supervised pretraining serves as a powerful catalyst, being especially advantageous when limited annotated data are available and efficient scaling of computational cost is important.

Cited by

• Are Vision Foundation Models Foundational for Electron Microscopy Image Segmentation?

Related

• Deep Generative Models-Assisted Automated Labeling for Electron Microscopy Images Segmentation
• Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation
• Ensemble learning and iterative training (ELIT) machine learning: applications towards uncertainty quantification and automated experiment in atom-resolved microscopy
• Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring
• Learning Generative Models of Tissue Organization with Supervised GANs