YOLO-Count: Differentiable Object Counting for Text-to-Image Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909716666384384 |
|---|---|
| author | Zeng, Guanning Zhang, Xiang Wang, Zirui Xu, Haiyang Chen, Zeyuan Li, Bingnan Tu, Zhuowen |
| author_facet | Zeng, Guanning Zhang, Xiang Wang, Zirui Xu, Haiyang Chen, Zeyuan Li, Bingnan Tu, Zhuowen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | YOLO-Count: Differentiable Object Counting for Text-to-Image Generation Zeng, Guanning Zhang, Xiang Wang, Zirui Xu, Haiyang Chen, Zeyuan Li, Bingnan Tu, Zhuowen Computer Vision and Pattern Recognition 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. |
| title | YOLO-Count: Differentiable Object Counting for Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00728 |