Enhancing Semantic Segmentation in High-Resolution TEM Images: A Comparative Study of Batch Normalization and Instance Normalization

Microscopy and Microanalysis, vol. 31

Abstract

Integrating deep learning into image analysis for transmission electron microscopy (TEM) holds significant promise for advancing materials science and nanotechnology. Deep learning is able to enhance image quality, to automate feature detection, and to accelerate data analysis, addressing the complex nature of TEM datasets. This capability is crucial for precise and efficient characterization of details on the nano-and microscale, e.g., facilitating more accurate and high-throughput analysis of nanoparticle structures. This study investigates the influence of batch normalization (BN) and instance normalization (IN) on the performance of deep learning models for semantic segmentation of high-resolution TEM images. Using U-Net and ResNet architectures, we trained models on two different datasets. Our results demonstrate that IN consistently outperforms BN, yielding higher Dice scores and Intersection over Union metrics. These findings underscore the necessity of selecting appropriate normalization methods to maximize the performance of deep learning models applied to TEM images.

Authors 2

1. Bashir Kazimi corresponding

   Forschungszentrum Jülich

   Affiliation as printed

   Institute for Advanced Simulation—Materials Data Science and Informatics (IAS-9), Forschungszentrum Jülich GmbH , Jülich 52425 ,

2. Stefan Sandfeld Aachen Chair of Materials Data Science and Materials Informatics Faculty 5 – Georesources and Materials Engineering

   RWTH Aachen University · Forschungszentrum Jülich

   Affiliation as printed

   Chair of Materials Data Science and Materials Informatics, Faculty 5—Georesources and Materials Engineering, RWTH Aachen University , Aachen 52056 ,

   Institute for Advanced Simulation—Materials Data Science and Informatics (IAS-9), Forschungszentrum Jülich GmbH , Jülich 52425 ,