Count Anything
:::info Stub — Full Engineering Breakdown Coming This paper has a linked code implementation and was featured on Hugging Face Papers with 2 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Mengqi Lei et al. |
| Year | 2026 |
| HF Upvotes | 2 |
| arXiv | 2605.30846 |
| Download | |
| Code | https://github.com/Mengqi-Lei/count-anything |
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: https://github.com/Mengqi-Lei/count-anything.
Engineering Breakdown
The Problem
Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models.
The Approach
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. Based on CLOC, we propose Count Anything, a generalist model for text-guided object counting.
Key Results
Code is available at: https://github.com/Mengqi-Lei/count-anything.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Generalist
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::