智能传感器的协调尺度：人群计数视觉基础模型的分辨率条件自适应
Harmonizing Scale for Intelligent Sensors: Resolution-Conditioned Adaptation of Vision Foundation Models for Crowd Counting.
摘要(中文译文)
尺度变化仍然是智能监控传感器在人群计数与定位任务中面临的根本性挑战。尽管近期的选择性继承方法通过多分辨率特征融合展现出良好前景，但这些方法通常依赖表征能力有限的传统CNN骨干网络。DINOv3等基础模型提供了强大的自监督表征，然而将冻结的DINOv3特征直接应用于选择性尺度感知计数并非易事：这些特征语义性强，但与密度估计或尺度条件继承需求并不直接对齐。本文提出D3-CalibCount，一种可训练参数高效的框架，用于将冻结的DINOv3表征适配于选择性尺度感知人群计数与定位。我们引入轻量级尺度协调适配器（Scale Harmonization Adapter，SHA），执行分辨率条件特征校准，将通用DINOv3表征转换为适合跨分辨率层级渐进继承的尺度选择性计数特征。在三个广泛使用的基准上的大量实验表明，相较于选择性继承基线，该方法取得了一致性提升，尤其是在严重尺度变化条件下。从部署角度看，该方法减少了网络的可训练部分，但冻结的DINOv3-L骨干仍比更轻量的CNN基线带来更高的推理成本。目标应用场景为基于摄像头的智能监控传感，即在配备GPU的监控节点上从视觉传感器输入执行人群密度估计。这些结果表明，对冻结基础特征进行轻量级适配是人群计数及其他密集预测任务的一个实用方向。
Abstract
Scale variation remains a fundamental challenge for intelligent surveillance sensors in crowd-counting and localization tasks. While recent selective inheritance methods have shown promise through multi-resolution feature fusion, they typically rely on conventional CNN backbones with limited representation capacity. Foundation models such as DINOv3 offer powerful self-supervised representations, yet directly applying frozen DINOv3 features to selective scale-aware counting is non-trivial: these features are semantically strong but not directly aligned with density estimation or scale-conditioned inheritance requirements. In this paper, we propose D3-CalibCount, a trainable-parameter-efficient framework for adapting frozen DINOv3 representations to selective scale-aware crowd counting and localization. We introduce a lightweight Scale Harmonization Adapter (SHA) that performs resolution-conditioned feature calibration, transforming generic DINOv3 representations into scale-selective counting features suitable for progressive inheritance across resolution levels. Extensive experiments on three widely used benchmarks show consistent improvements over selective inheritance baselines, especially under severe scale variation. From a deployment perspective, the method reduces the trainable portion of the network, while the frozen DINOv3-L backbone still introduces a higher inference cost than lighter CNN baselines. The target application scenario is camera-based intelligent surveillance sensing, where crowd density estimation is performed from visual sensor inputs at GPU-backed monitoring nodes. These results suggest that lightweight adaptation of frozen foundation features is a practical direction for crowd counting and other dense prediction tasks.
如何引用
AMA
Huan Xu, Zhiheng Chen, Sirou Shen, Haibin You, Chih-Cheng Chen. Harmonizing Scale for Intelligent Sensors: Resolution-Conditioned Adaptation of Vision Foundation Models for Crowd Counting.. Sensors (Basel, Switzerland). 2026; doi:10.3390/s26103047.
APA
Huan Xu, Zhiheng Chen, Sirou Shen, Haibin You, Chih-Cheng Chen (2026). Harmonizing Scale for Intelligent Sensors: Resolution-Conditioned Adaptation of Vision Foundation Models for Crowd Counting.. Sensors (Basel, Switzerland). https://doi.org/10.3390/s26103047
GB/T 7714
Huan Xu, Zhiheng Chen, Sirou Shen, Haibin You, Chih-Cheng Chen. Harmonizing Scale for Intelligent Sensors: Resolution-Conditioned Adaptation of Vision Foundation Models for Crowd Counting.[J]. Sensors (Basel, Switzerland), 2026 doi:10.3390/s26103047.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出