LIR-Mamba: consolidating YOLO and selective SSM with global-local scanning for robust infrared small target detection under laser interference
Tianyi Chen, Xiangyi Hu, Jiafen Wang · 2026
Read LIR-Mamba: consolidating YOLO and selective SSM with global-local scanning for robust infrared small target detection under laser interference by Tianyi Chen, Xiangyi Hu, Jiafen Wang (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/PMC13427715.txt.
Description
Tianyi Chen, Xiangyi Hu, and Jiafen Wang introduce, in a 2026 study, a detector for tiny infrared targets seen through laser glare. Defense sensors must spot small hot objects even when an enemy laser floods the image with glare and speckle. Standard networks miss wide context, while transformer models cost too much computing for small field devices. Their system, LIR-Mamba, joins the fast YOLO detector family with a state-space model that scans images both locally and globally.
The scanning design keeps small hot spots from washing out in noise. In tests it scored about 96 percent on a standard accuracy measure while running at 66 frames per second. Rival detectors, including recent YOLO and transformer versions, trailed on accuracy or toughness against jamming. Real-time defense imaging on modest hardware is the intended payoff.
Catalog record
| CREATOR | Tianyi Chen, Xiangyi Hu, Jiafen Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |