Scaling deep learning for material imaging with a pseudo 3D model for domain transfer
Kunning Tang, Ryan T. Armstrong, Peyman Mostaghimi, Yufu Niu, Quentin Meyer, Chuan Zhao, Donal P. Finegan, Melissa Popeil, Kamaljit Singh, Hannah Menke, Alexandros Patsoukis Dimou, Tom Bultreys, Arjen Mascini, Mark Knackstedt, Ying Da Wang · 2025
Read Scaling deep learning for material imaging with a pseudo 3D model for domain transfer by Kunning Tang, Ryan T. Armstrong, Peyman Mostaghimi, Yufu Niu, Quentin Meyer, Chuan Zhao, Donal P. Finegan, Melissa Popeil, Kamaljit Singh, Hannah Menke, Alexandros Patsoukis Dimou, Tom Bultreys, Arjen Mascini, Mark Knackstedt, Ying Da Wang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12722266.txt.
Description
Kunning Tang and co-authors teach one image model to serve many material scans. Their 2025 paper deals with 3D X-ray imaging of rocks, fuel cells, and batteries, where scan settings vary and models falter on fresh sets. Retraining for each set caps real use. Their network first shifts any 3D image into one shared domain, so old trained models can read it as is.
Tests span fast rock scans, fuel cell shots, battery images from mixed sources, and fine sorting under varied settings. One run shifted a tera-scale volume on a single graphics card. The team claims big savings in compute and a sturdier path for deep learning in materials work.
Catalog record
| CREATOR | Kunning Tang, Ryan T. Armstrong, Peyman Mostaghimi, Yufu Niu, Quentin Meyer, Chuan Zhao, Donal P. Finegan, Melissa Popeil, Kamaljit Singh, Hannah Menke, Alexandros Patsoukis Dimou, Tom Bultreys, Arjen Mascini, Mark Knackstedt, Ying Da Wang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 108 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |