EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Point-Supervised Infrared Small-Target Detection via Gradient-Guided Minimum Variance Growth and Deep Iterative Refinement

Haoran Shi, Guoyong Cai, Guangrui Lv, Liusheng Wei

Electronics · 2026-04-23 · 15 (9) · 1791

DOI: 10.3390/electronics15091791 ↗

At a glance

Journal article in Electronics, published online on 2026-04-23. Written by Haoran Shi and 3 co-authors. Cited 2 times so far (Crossref); 40 references. The full text is freely available (open access, CC BY 4.0). Funded by: Natural Science Foundation of Guangxi, Research Foundation Ability Enhancement Project for Young and Middle Aged Teachers in Guangxi Universities, Project of Guangxi Key Laboratory of Trusted Software.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Infrared small-target detection (IRSTD) has benefited from deep learning, yet most existing methods still rely on dense pixel-level annotations, which are costly and often unreliable for tiny and weak targets. Point supervision offers a more practical alternative, but current point-supervised methods usually construct pseudo-labels based on the distance between pixels and annotated points or cluster centers, which introduces spatial bias and may miss genuine target pixels away from these reference points. To address this issue, we propose GMVG-DIR, a point-supervised IRSTD framework that combines Gradient-Guided Minimum Variance Growth (GMVG) with Deep Iterative Refinement (DIR). GMVG first estimates target likelihood from gradient-guided aggregation of contour closure and edge responses and then converts it into structurally coherent pseudo-labels via the Minimum Variance Growth filter, without relying on distance cues. DIR further improves the pseudo-labels by incorporating reliable semantic guidance into an iterative refinement process, thereby reducing error propagation. By emphasizing structural consistency rather than spatial proximity, the proposed framework better preserves irregular target shapes and remains robust to point-label deviation. Extensive experiments on NUDT-SIRST, IRSTD-1k, and NUAA-SIRST show that GMVG-DIR improves pseudo-label fidelity and achieves competitive point-supervised performance across multiple dataset-backbone settings, especially in IoU and Pd.

Funding

  • Natural Science Foundation of Guangxi
  • Research Foundation Ability Enhancement Project for Young and Middle Aged Teachers in Guangxi Universities
  • Project of Guangxi Key Laboratory of Trusted Software

Cite

APA

Shi, H., Cai, G., Lv, G., & Wei, L. (2026). Point-Supervised Infrared Small-Target Detection via Gradient-Guided Minimum Variance Growth and Deep Iterative Refinement. Electronics, 15(9), 1791. https://doi.org/10.3390/electronics15091791

Vancouver

Shi H, Cai G, Lv G, Wei L. Point-Supervised Infrared Small-Target Detection via Gradient-Guided Minimum Variance Growth and Deep Iterative Refinement. Electronics. 2026;15(9):1791. doi:10.3390/electronics15091791

BibTeX
@article{Shi2026,
  author = {Shi, Haoran and Cai, Guoyong and Lv, Guangrui and Wei, Liusheng},
  title = {Point-Supervised Infrared Small-Target Detection via Gradient-Guided Minimum Variance Growth and Deep Iterative Refinement},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {1791},
  doi = {10.3390/electronics15091791}
}
Start for free →