CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Jiang, Ruixiang, Liu, Lingbo, Chen, Changwen
–arXiv.org Artificial Intelligence
Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level visual representations for dense prediction. Moreover, we design a hierarchical patch-text interaction module to propagate semantic information across different resolution levels of visual features. Benefiting from the full exploitation of the rich image-text alignment knowledge of pretrained VLMs, our method effectively generates high-quality density maps for objects-of-interest. Extensive experiments on FSC-147, CARPK, and ShanghaiTech crowd counting datasets demonstrate state-of-the-art accuracy and generalizability of the proposed method. Code is available: https://github.com/songrise/CLIP-Count.
arXiv.org Artificial Intelligence
Aug-10-2023
- Country:
- North America
- United States > New York
- New York County > New York City (0.04)
- Canada > Ontario
- National Capital Region > Ottawa (0.06)
- United States > New York
- Asia
- China > Hong Kong (0.04)
- Middle East > Israel
- Tel Aviv District > Tel Aviv (0.04)
- North America
- Genre:
- Research Report > New Finding (0.66)
- Technology: