Photonics· 2026Q2
Semantic-Guided Enhanced UIU-Net for Infrared Small Target Detection
- 0citations
- Q2SCImago
- 2026year
Short summary
A new SGUIU-Net model improves infrared small target detection IoU by 0.0180 (to 0.7995) on the SIRST benchmark by integrating attention, deep supervision, and semantic guidance.
AI-generated from the title and abstract; the full text is not read.
Key points
- The SGUIU-Net model integrates multiple advanced modules (RSUs, CBAM, Focal–Dice, SGCA-Fusion) for infrared small target detection.
- On the SIRST benchmark, SGUIU-Net achieved an IoU of 0.7995 ± 0.0011, outperforming the baseline by 0.0180.
- The model also showed improvements on IRSTD-1K (IoU 0.7125) and SIRST-V2 (IoU 0.7364) datasets.
- Performance gains were accompanied by an increase in parameters from 50.54M to 106.31M and a decrease in FPS from 50.05 to 32.53.
AI-generated from the title and abstract; the full text is not read.
Abstract
Infrared small-target detection is commonly implemented as binary pixel-level segmentation and localization but remains challenging because targets occupy very few pixels and are embedded in complex backgrounds. This paper develops the Semantic-Guided Enhanced UIU-Net (SGUIU-Net) as a task-specific extension of U-Net in U-Net (UIU-Net) by combining Dilated Residual U-blocks (RSUs), the Convolutional Block Attention Module (CBAM), Focal–Dice deep supervision, and Semantic-Guided Cross-Attention Fusion (SGCA-Fusion). Experiments are conducted on the 427-image SIRST benchmark and the auxiliary IRSTD-1K and SIRST-V2 datasets. On SIRST, the full model obtains an IoU of 0.7995 ± 0.0011 and an nIoU of 0.7572 ± 0.0012 over three independent runs, improving the matched UIU-Net baseline means by 0.0180 and 0.0057, respectively. The model also improves IoU/nIoU from 0.6379/0.6057 to 0.7125/0.6787 on IRSTD-1K and from 0.7215/0.6832 to 0.7364/0.6937 on SIRST-V2. These gains are accompanied by an increase from 50.54 M to 106.31 M parameters and a decrease from 50.05 to 32.53 FPS at 320 × 320 resolution.
The authors' abstract, as published at the source. Photonics, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Aerospace Engineering
Aerospace EngineeringEngineering