Semi-Supervised Radar Work Mode Recognition Based on Contrastive Learning
Peishan Sun, Mingyang Du, Zhihui Li, Xuan Chen, Junpeng Shi · 2025
Read Semi-Supervised Radar Work Mode Recognition Based on Contrastive Learning by Peishan Sun, Mingyang Du, Zhihui Li, Xuan Chen, Junpeng Shi (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-12736939.txt.
Description
Peishan Sun, Mingyang Du, Zhihui Li, Xuan Chen, and Junpeng Shi build a radar mode reader that learns from mostly unlabeled signals. Their study was published in twenty twenty-five. Fine-grained radar reading with deep learning normally needs heaps of labeled data, which is costly to make.
Their setup joins three branches in one system. Two contrast methods teach the model to match like signals and split unlike ones, and special steps handle warped pulses. On two hard test sets, the method lifted accuracy by wide margins while using only a tenth of the labeled data. The authors say that sets a new best mark for this task. The work matters for defense and sensing teams that cannot label vast signal stores by hand.
Catalog record
| CREATOR | Peishan Sun, Mingyang Du, Zhihui Li, Xuan Chen, Junpeng Shi |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |