Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy
This work addresses data efficiency and computational scaling for electron microscopy tasks, but it is incremental as it applies existing self-supervised and GAN methods to a new domain.
The paper tackles the problem of limited annotated data in electron microscopy by using self-supervised learning with GANs for pretraining, resulting in fine-tuned models that achieve faster convergence and better performance, with lower complexity models outperforming more complex ones.
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.