Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.02301 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914783517736960 |
|---|---|
| author | Ting, Pan Lin, Jianfeng Yu, Wenhao Zhang, Wenlong Chen, Xiaoying Zhang, Jinlu Huang, Binqiang |
| author_facet | Ting, Pan Lin, Jianfeng Yu, Wenhao Zhang, Wenlong Chen, Xiaoying Zhang, Jinlu Huang, Binqiang |
| contents | Object counting is a challenging task with broad application prospects in security surveillance, traffic management, and disease diagnosis. Existing object counting methods face a tri-fold challenge: achieving superior performance, maintaining high generalizability, and minimizing annotation costs. We develop a novel training-free class-agnostic object counter, TFCounter, which is prompt-context-aware via the cascade of the essential elements in large-scale foundation models. This approach employs an iterative counting framework with a dual prompt system to recognize a broader spectrum of objects varying in shape, appearance, and size. Besides, it introduces an innovative context-aware similarity module incorporating background context to enhance accuracy within messy scenes. To demonstrate cross-domain generalizability, we collect a novel counting dataset named BIKE-1000, including exclusive 1000 images of shared bicycles from Meituan. Extensive experiments on FSC-147, CARPK, and BIKE-1000 datasets demonstrate that TFCounter outperforms existing leading training-free methods and exhibits competitive results compared to trained counterparts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02301 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TFCounter:Polishing Gems for Training-Free Object Counting Ting, Pan Lin, Jianfeng Yu, Wenhao Zhang, Wenlong Chen, Xiaoying Zhang, Jinlu Huang, Binqiang Computer Vision and Pattern Recognition 68 Object counting is a challenging task with broad application prospects in security surveillance, traffic management, and disease diagnosis. Existing object counting methods face a tri-fold challenge: achieving superior performance, maintaining high generalizability, and minimizing annotation costs. We develop a novel training-free class-agnostic object counter, TFCounter, which is prompt-context-aware via the cascade of the essential elements in large-scale foundation models. This approach employs an iterative counting framework with a dual prompt system to recognize a broader spectrum of objects varying in shape, appearance, and size. Besides, it introduces an innovative context-aware similarity module incorporating background context to enhance accuracy within messy scenes. To demonstrate cross-domain generalizability, we collect a novel counting dataset named BIKE-1000, including exclusive 1000 images of shared bicycles from Meituan. Extensive experiments on FSC-147, CARPK, and BIKE-1000 datasets demonstrate that TFCounter outperforms existing leading training-free methods and exhibits competitive results compared to trained counterparts. |
| title | TFCounter:Polishing Gems for Training-Free Object Counting |
| topic | Computer Vision and Pattern Recognition 68 |
| url | https://arxiv.org/abs/2405.02301 |