Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection

2026-03-17

AI Summary

This work addresses the challenge of infrared small target detection, which typically relies on costly pixel-level annotations due to the targets’ weak signatures and ambiguous boundaries. To alleviate this burden, we propose a Point-to-Mask framework that transforms sparse point annotations into compact masks via a physics-driven adaptive mask generation (PAMG) module. We further introduce a radius-aware point regression network (RPR-Net) to jointly optimize target center localization and effective radius estimation, integrating spatiotemporal motion cues and a pseudo-labeling closed-loop refinement strategy. To our knowledge, this is the first approach to achieve efficient mask-level detection from arbitrary point supervision. Evaluated on our newly curated SIRSTD-Pixel dataset, the method substantially reduces annotation costs while approaching full-supervision performance, achieving both high accuracy and efficient inference.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Infrared small target detection (IRSTD) methods predominantly formulate the task as pixel-level segmentation, which requires costly dense annotations and is not well suited to tiny targets with weak texture and ambiguous boundaries. To address this issue, we propose Point-to-Mask, a framework that bridges low-cost point supervision and mask-level detection through two components: a Physics-driven Adaptive Mask Generation (PAMG) module that converts point annotations into compact target masks and geometric cues, and a lightweight Radius-aware Point Regression Network (RPR-Net) that reformulates IRSTD as target center localization and effective radius regression using spatiotemporal motion cues. The two modules form a closed loop: PAMG generates pseudo masks and geometric supervision during training, while the geometric predictions of RPR-Net are fed back to PAMG for pixel-level mask recovery during inference. To facilitate systematic evaluation, we further construct SIRSTD-Pixel, a sequential dataset with refined pixel-level annotations. Experiments show that the proposed framework achieves strong pseudo-label quality, high detection accuracy, and efficient inference, approaching full-supervision performance under point-supervised settings with substantially lower annotation cost. Code and datasets will be available at: https://github.com/GaoScience/point-to-mask.

Problem

• Infrared small target detection
• point annotation
• mask-level detection
• weak texture
• ambiguous boundaries

Innovation

• Point-to-Mask
• Physics-driven Adaptive Mask Generation
• Radius-aware Point Regression Network
• Infrared Small Target Detection
• Point Supervision