Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911997558259712 |
|---|---|
| author | Srinivas, Sakhinana Sagar Sarkar, Rajat Kumar Gangasani, Sreeja Runkana, Venkataramana |
| author_facet | Srinivas, Sakhinana Sagar Sarkar, Rajat Kumar Gangasani, Sreeja Runkana, Venkataramana |
| contents | Material characterization using electron micrographs is a crucial but challenging task with applications in various fields, such as semiconductors, quantum materials, batteries, etc. The challenges in categorizing electron micrographs include but are not limited to the complexity of patterns, high level of detail, and imbalanced data distribution(long-tail distribution). Existing methods have difficulty in modeling the complex relational structure in electron micrographs, hindering their ability to effectively capture the complex relationships between different spatial regions of micrographs. We propose a hypergraph neural network(HgNN) backbone architecture, a conceptually alternative approach, to better model the complex relationships in electron micrographs and improve material characterization accuracy. By utilizing cost-effective GPU hardware, our proposed framework outperforms popular baselines. The results of the ablation studies demonstrate that the proposed framework is effective in achieving state-of-the-art performance on benchmark datasets and efficient in terms of computational and memory requirements for handling large-scale electron micrograph-based datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11351 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodes Srinivas, Sakhinana Sagar Sarkar, Rajat Kumar Gangasani, Sreeja Runkana, Venkataramana Machine Learning Artificial Intelligence Material characterization using electron micrographs is a crucial but challenging task with applications in various fields, such as semiconductors, quantum materials, batteries, etc. The challenges in categorizing electron micrographs include but are not limited to the complexity of patterns, high level of detail, and imbalanced data distribution(long-tail distribution). Existing methods have difficulty in modeling the complex relational structure in electron micrographs, hindering their ability to effectively capture the complex relationships between different spatial regions of micrographs. We propose a hypergraph neural network(HgNN) backbone architecture, a conceptually alternative approach, to better model the complex relationships in electron micrographs and improve material characterization accuracy. By utilizing cost-effective GPU hardware, our proposed framework outperforms popular baselines. The results of the ablation studies demonstrate that the proposed framework is effective in achieving state-of-the-art performance on benchmark datasets and efficient in terms of computational and memory requirements for handling large-scale electron micrograph-based datasets. |
| title | Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodes |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.11351 |