EMamba: A MoE-enhanced state space network for robust steel surface defect detection
Haiyan Yang, Peng Wang, Yangyang Liu · 2026
Read EMamba: A MoE-enhanced state space network for robust steel surface defect detection by Haiyan Yang, Peng Wang, Yangyang Liu (2026) 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/plos-pone-0358866.txt.
Description
Yang and two co-authors published a 2026 PLOS ONE paper on software that finds flaws on steel surfaces. Their network, EMamba, adds a mixture-of-experts design to a state space model. The goal is sturdy detection even when lighting or steel type changes. Missed cracks in steel can fail later in bridges or machines, so reliable automated inspection has real safety value.
Catalog record
| CREATOR | Haiyan Yang, Peng Wang, Yangyang Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 98005 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |