---
title: "Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation"
authors:
  - "Yuanhang Yao"
  - "Ping Qian"
  - "Zhu Liu"
  - "Long Ma"
  - "Weimin Wang"
doi: "10.24963/ijcai.2026/224"
url: "https://ijcai.org/proceedings/2026/224"
pdf: "https://ijcai.org/proceedings/2026/0224.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2010-2018"
track: "Main Track"
keywords:
  - "Computer Vision: Transfer, low-shot, semi- and un- supervised learning"
  - "Computer Vision: Segmentation, grouping and shape analysis"
---

# Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation

Yuanhang Yao, Ping Qian, Zhu Liu, Long Ma, Weimin Wang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2010-2018. DOI: [10.24963/ijcai.2026/224](https://doi.org/10.24963/ijcai.2026/224)

## Abstract

Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop adapts a VFM-embedded teacher on reweighted training samples, while the outer loop transfers validation-guided knowledge to a lightweight student to mitigate pseudo-label noise and training-set bias. We further introduce Semantic-Conditioned Affine Modulation (SCAM) to inject VFM semantics into CNN features at multiple layers. In addition, a dynamic collaborative learning strategy with cluster-level sample reweighting enhances robustness to imperfect pseudo-masks. Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability. Our code is available at https://github.com/yuanhang-yao/semantic-prior.