Count Anything (2 minute read)

# Count Anything
Source: [https://arxiv.org/abs/2605.30846](https://arxiv.org/abs/2605.30846)
## Title:Count Anything

[View PDF](https://arxiv.org/pdf/2605.30846)

> Abstract: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:[this https URL](https://github.com/Mengqi-Lei/count-anything)\.

## Submission history

From: Mengqi Lei \[[view email](https://arxiv.org/show-email/167da367/2605.30846)\] **\[v1\]**Fri, 29 May 2026 05:08:31 UTC \(41,518 KB\)