Semi-Supervised Structural Prior-Guided Network for Space Target Component Segmentation in ISAR Images
Yonghua He, Aoxiang Pan, Yonggang Li, Jiahao Wang, Wei Qu, Weigang Zhu, Wenhang Ji · 2026
Read Semi-Supervised Structural Prior-Guided Network for Space Target Component Segmentation in ISAR Images by Yonghua He, Aoxiang Pan, Yonggang Li, Jiahao Wang, Wei Qu, Weigang Zhu, Wenhang Ji (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/PMC13469483.txt.
Description
Yonghua He and co-authors introduce SSPNet in 2026, a network that segments parts of space objects in radar images while needing few hand labels. Analysts use inverse synthetic aperture radar pictures to identify satellite components, yet pixel level labels are scarce and costly. Similar looking parts also confuse standard models.
The design adds shape and edge hints drawn from domain knowledge into channels that respond weakly. A gated transformer encoder widens the feature space so classes separate more cleanly. Across several label budgets, SSPNet beat rival methods on segmentation scores. It stayed robust even with very few labels and heavy noise. The authors argue that built in structural knowledge, not just more data, drives the gain.
Catalog record
| CREATOR | Yonghua He, Aoxiang Pan, Yonggang Li, Jiahao Wang, Wei Qu, Weigang Zhu, Wenhang Ji |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |