We propose YOLO-Count, a differentiable open-vocabulary object counting model that tackles both general counting challenges and enables precise quantity control for text-to-image (T2I) generation. A core contribution is the 'cardinality' map, a novel regression target that accounts for variations in object size and spatial distribution. Leveraging representation alignment and a hybrid strong-weak supervision scheme, YOLO-Count bridges the gap between open-vocabulary counting and T2I generation control. Its fully differentiable architecture facilitates gradient-based optimization, enabling accurate object count estimation and fine-grained guidance for generative models. Extensive experiments demonstrate that YOLO-Count achieves state-of-the-art counting accuracy while providing robust and effective quantity control for T2I systems.
@article{arxiv.2508.00728,
title = {YOLO-Count: Differentiable Object Counting for Text-to-Image Generation},
author = {Guanning Zeng and Xiang Zhang and Zirui Wang and Haiyang Xu and Zeyuan Chen and Bingnan Li and Zhuowen Tu},
journal= {arXiv preprint arXiv:2508.00728},
year = {2025}
}