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 domain$\unicode{x2010}$pretrained
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 irradiation$\unicode{x2010}$induced amorphous
fronts in thin films used for catalysis and electronics. This method has
potential for "on$\unicode{x2010}$the$\unicode{x2010}$fly" segmentation to
guide emerging automated electron microscopes.

使用无监督分割方法对电子显微镜图像进行分割，以跟踪用于催化和电子领域的薄膜中辐照引起的非晶前沿，为自动化电子显微镜提供指导。

电子显微技术中无监督分割的辐射诱导有序 - 无序相变

Unsupervised segmentation of irradiation$\unicode{x2010}$induced  order$\unicode{x2010}$disorder phase transitions in electron microscopy

Complex networks usually expose community structure with groups of nodes
sharing many links with the other nodes in the same group and relatively few
with the nodes of the rest. This feature captures valuable information about
the organization and even the evolution of the network. Over the last decade, a
great number of algorithms for community detection have been proposed to deal
with the increasingly complex networks. However, the problem of doing this in a
private manner is rarely considered. In this paper, we solve this problem under
differential privacy, a prominent privacy concept for releasing private data.
We analyze the major challenges behind the problem and propose several schemes
to tackle them from two perspectives: input perturbation and algorithm
perturbation. We choose Louvain method as the back-end community detection for
input perturbation schemes and propose the method LouvainDP which runs Louvain
algorithm on a noisy super-graph. For algorithm perturbation, we design
ModDivisive using exponential mechanism with the modularity as the score. We
have thoroughly evaluated our techniques on real graphs of different sizes and
verified their outperformance over the state-of-the-art.

本篇研究基于微分隐私解决复杂网络隐私保护问题，提出了基于 Louvain 方法的输入扰动方案 LouvainDP 和基于指数机制的算法扰动方案 ModDivisive，并在真实数据集上进行了充分评估，验证了其优越性。