# Assessing the Visual Enumeration Abilities of Specialized Counting Architectures and Vision-Language Models

arXiv: https://arxiv.org/abs/2512.15254 · HTML: https://mlsanity.com/paper/2512.15254/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [Few-shot Object Counting and Detection](https://mlsanity.com/paper/2207.10988/) (2022)
- [Learning to Count Objects in Natural Images for Visual Question Answering](https://mlsanity.com/paper/1802.05766/) (2018)
- [Point, Segment and Count: A Generalized Framework for Object Counting](https://mlsanity.com/paper/2311.12386/) (2023)
- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [Completely Self-Supervised Crowd Counting via Distribution Matching](https://mlsanity.com/paper/2009.06420/) (2020)
- [T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting](https://mlsanity.com/paper/2502.20625/) (2025)
- [Interpretable Counting for Visual Question Answering](https://mlsanity.com/paper/1712.08697/) (2017)
- [Understanding the impact of mistakes on background regions in crowd counting](https://mlsanity.com/paper/2003.13759/) (2020)
- [Cross-head Supervision for Crowd Counting with Noisy Annotations](https://mlsanity.com/paper/2303.09245/) (2023)
- [Visual Enumeration Remains Challenging for Multimodal Generative AI](https://mlsanity.com/paper/2402.03328/) (2024)
- [Sequential Enumeration in Large Language Models](https://mlsanity.com/paper/2512.04727/) (2025)
- [Estimating the distribution of numerosity and non-numerical visual magnitudes in natural scenes using computer vision](https://mlsanity.com/paper/2409.11028/) (2024)

## Built on by (most cited first, 1 of 1)

- [Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges](https://mlsanity.com/paper/2608.23845/) (2026)

## Abstract (arXiv)

Counting the number of items in a visual scene remains a fundamental yet challenging task in computer vision. Traditional approaches to solving this problem rely on domain-specific counting architectures, which are trained using datasets annotated with a predefined set of object categories. However, recent progress in creating large-scale multimodal vision-language models (VLMs) suggests that these domain-general architectures may offer a flexible alternative for open-set object counting. In this study, we therefore systematically compare the performance of state-of-the-art specialized counting architectures against VLMs on two popular counting datasets, as well as on a novel benchmark specifically created to have a finer-grained control over the visual properties of test images. Our findings show that most VLMs can approximately enumerate the number of items in a visual scene, matching or even surpassing the performance of specialized computer vision architectures. Notably, enumeration accuracy significantly improves when VLMs are prompted to generate intermediate representations (i.e., locations and verbal labels) of each object to be counted. Nevertheless, none of the models can reliably count the number of objects in complex visual scenes, showing that further research is still needed to create AI systems that can reliably deploy counting procedures in realistic environments.