Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy

arXiv (Cornell University)

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.

Authors 3

1. Bashir Kazimi

   Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH , Jülich , IAS- 9 , Germany

2. Karina Ruzaeva

   Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH , Jülich , IAS- 9 , Germany

3. Stefan Sandfeld Aachen

   RWTH Aachen University · Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH , Jülich , IAS- 9 , Germany

   RWTH Aachen University , Aachen , Germany