# Unsupervised segmentation of irradiationunicodex2010induced orderunicodex2010disorder phase transitions in electron microscopy

arXiv: https://arxiv.org/abs/2311.08585 · HTML: https://mlsanity.com/paper/2311.08585/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Builds on (most cited first, 7 of 7)

- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering](https://mlsanity.com/paper/2212.05853/) (2022)
- [Machine Learning Pipeline for Segmentation and Defect Identification from High Resolution Transmission Electron Microscopy Data](https://mlsanity.com/paper/2001.05022/) (2020)
- [Deep Learning Segmentation of Complex Features in Atomic-Resolution Phase Contrast Transmission Electron Microscopy Images](https://mlsanity.com/paper/2012.05322/) (2020)
- [An Automated Scanning Transmission Electron Microscope Guided by Sparse Data Analytics](https://mlsanity.com/paper/2109.14772/) (2021)
- [STEM image analysis based on deep learning: identification of vacancy defects and polymorphs of MoS2](https://mlsanity.com/paper/2206.04272/) (2022)
- [Generalization Across Experimental Parameters in Machine Learning Analysis of High Resolution Transmission Electron Microscopy Datasets](https://mlsanity.com/paper/2306.11853/) (2023)

## Built on by (most cited first, 1 of 1)

- [Revealing the Evolution of Order in Materials Microstructures Using Multi-Modal Computer Vision](https://mlsanity.com/paper/2411.09896/) (2024)

## Abstract (arXiv)

We present a method for the unsupervised segmentation of electron microscopy images, which are powerful descriptors of materials and chemical systems. Images are oversegmented into overlapping chips, and similarity graphs are generated from embeddings extracted from a domainunicodex2010pretrained convolutional neural network (CNN). The Louvain method for community detection is then applied to perform segmentation. The graph representation provides an intuitive way of presenting the relationship between chips and communities. We demonstrate our method to track irradiationunicodex2010induced amorphous fronts in thin films used for catalysis and electronics. This method has potential for "onunicodex2010theunicodex2010fly" segmentation to guide emerging automated electron microscopes.