Count Anything
Count Anything
- Tsinghua University（清华大学）
- China University of Geosciences, Wuhan（武汉地质大学）
- State Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室）
- National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）
- Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出跨域文本引导的目标计数模型Count Anything，通过双粒度实例枚举和互补计数融合，在统一基准CLOC上实现多域泛化。
AI中文摘要：
尽管通用视觉模型取得了快速进展，目标计数仍然分散在特定领域的数据集和任务公式中。现有的计数模型通常针对人群、车辆、细胞、农作物或遥感目标等场景定制，因此难以跨类别、视觉域、目标尺度和密度分布进行泛化。在本文中，我们研究了跨域的文本引导目标计数，其中模型以图像和自然语言查询为输入，并返回一组基于实例的目标点，其基数给出计数。这种公式将类别条件计数与可解释的空间定位统一起来。为了支持这一设置，我们构建了CLOC，一个跨域大规模目标计数数据集，将多样化的公共数据源重组为统一的基准。CLOC涵盖六个视觉域：通用场景、遥感、组织病理学、细胞显微镜、农业和微生物学，包含约22万张图像、619个类别和1500万个目标实例。基于CLOC，我们提出了Count Anything，一个用于文本引导目标计数的通用模型。与主导计数模型的密度图方法不同，Count Anything采用离散实例点并执行双粒度实例枚举。区域级稀疏计数器为大而稀疏的目标提供目标级锚点，而像素级密集计数器通过密集点预测处理小、拥挤和弱边界目标。点中心监督策略能够从异构标注中学习，互补计数融合以无参数方式结合两个计数器。大量实验表明，Count Anything实现了强准确性和多域泛化，优于现有的开放世界计数方法。代码可在：https://github.com/Mengqi-Lei/count-anything 获取。
英文摘要：
Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing counting models are often tailored to scenarios such as crowds, vehicles, cells, crops, or remote-sensing objects, and thus struggle to generalize across categories, visual domains, object scales, and density distributions. In this paper, we study text-guided object counting across domains, where a model takes an image and a natural-language query as input and returns an instance-grounded set of target points whose cardinality gives the count. This formulation unifies category-conditioned counting with interpretable spatial localization. To support this setting, we construct CLOC, a Cross-domain Large-scale Object Counting dataset that reorganizes diverse public data sources into a unified benchmark. CLOC covers six visual domains: General Scene, Remote Sensing, Histopathology, Cellular Microscopy, Agriculture, and Microbiology, with about 220K images, 619 categories, and 15M object instances. Based on CLOC, we propose Count Anything, a generalist model for text-guided object counting. Unlike density-map-based methods, which dominate counting models, Count Anything adopts discrete instance points and performs dual-granularity instance enumeration. A Region-level Sparse Counter provides object-level anchors for large and sparse targets, while a Pixel-level Dense Counter handles small, crowded, and weakly bounded targets via dense point prediction. A point-centric supervision strategy enables learning from heterogeneous annotations, and Complementary Count Fusion combines both counters in a parameter-free manner. Extensive experiments show that Count Anything achieves strong accuracy and multi-domain generalization, outperforming existing open-world counting methods. Code is available at: https://github.com/Mengqi-Lei/count-anything.
