EMCNet : Graph-Nets for Electron Micrographs Classification

2024/08/21 by Srinivas, Sakhinana Sagar, Sarkar, Rajat Kumar, Runkana, Venkataramana
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2409.03767

Abstract

Characterization of materials via electron micrographs is an important and challenging task in several materials processing industries. Classification of electron micrographs is complex due to the high intra-class dissimilarity, high inter-class similarity, and multi-spatial scales of patterns. However, existing methods are ineffective in learning complex image patterns. We propose an effective end-to-end electron micrograph representation learning-based framework for nanomaterial identification to overcome the challenges. We demonstrate that our framework outperforms the popular baselines on the open-source datasets in nanomaterials-based identification tasks. The ablation studies are reported in great detail to support the efficacy of our approach.

Related

• Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models
• Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodes
• EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation
• Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models
• Deep Generative Models-Assisted Automated Labeling for Electron Microscopy Images Segmentation