# Expanding Zero-Shot Object Counting with Rich Prompts

arXiv: https://arxiv.org/abs/2505.15398 · HTML: https://mlsanity.com/paper/2505.15398/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning](https://mlsanity.com/paper/1609.04453/) (2016)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [CounTR: Transformer-based Generalised Visual Counting](https://mlsanity.com/paper/2208.13721/) (2022)
- [A Low-Shot Object Counting Network With Iterative Prototype Adaptation](https://mlsanity.com/paper/2211.08217/) (2022)
- [CountGD: Multi-Modal Open-World Counting](https://mlsanity.com/paper/2407.04619/) (2024)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting](https://mlsanity.com/paper/2312.16580/) (2023)
- [Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision](https://mlsanity.com/paper/2205.10203/) (2022)
- [Open-world Text-specified Object Counting](https://mlsanity.com/paper/2306.01851/) (2023)
- [Point, Segment and Count: A Generalized Framework for Object Counting](https://mlsanity.com/paper/2311.12386/) (2023)
- [Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting](https://mlsanity.com/paper/2305.04440/) (2023)
- [Completely Self-Supervised Crowd Counting via Distribution Matching](https://mlsanity.com/paper/2009.06420/) (2020)
- [Zero-shot Object Counting with Good Exemplars](https://mlsanity.com/paper/2407.04948/) (2024)
- [T-Rex: Counting by Visual Prompting](https://mlsanity.com/paper/2311.13596/) (2023)
- [DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting](https://mlsanity.com/paper/2304.00741/) (2023)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)

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

- [Object Counting with GPT-4o and GPT-5: A Comparative Study](https://mlsanity.com/paper/2512.03233/) (2025)

## Abstract (arXiv)

Expanding pre-trained zero-shot counting models to handle unseen categories requires more than simply adding new prompts, as this approach does not achieve the necessary alignment between text and visual features for accurate counting. We introduce RichCount, the first framework to address these limitations, employing a two-stage training strategy that enhances text encoding and strengthens the model's association with objects in images. RichCount improves zero-shot counting for unseen categories through two key objectives: (1) enriching text features with a feed-forward network and adapter trained on text-image similarity, thereby creating robust, aligned representations; and (2) applying this refined encoder to counting tasks, enabling effective generalization across diverse prompts and complex images. In this manner, RichCount goes beyond simple prompt expansion to establish meaningful feature alignment that supports accurate counting across novel categories. Extensive experiments on three benchmark datasets demonstrate the effectiveness of RichCount, achieving state-of-the-art performance in zero-shot counting and significantly enhancing generalization to unseen categories in open-world scenarios.