VQCounter: Designing Visual Prompt Queue for Accurate Open-World Counting
Authors: Fanfan Ye, Yiqi Fan, Qiaoyong Zhong, Shicai Yang, Di Xie, Jie Song, Mingli Song
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on the FSC147 and CARPK datasets demonstrate that VQCounter achieves state-of-the-art performance in both zero-shot and few-shot settings, significantly outperforming existing methods across nearly all evaluations. We validate VQCounter through comprehensive experiments on two well-established datasets, namely FSC147 [Ranjan et al., 2021] and CARPK [Hsieh et al., 2017]. The results clearly illustrate that VQCounter substantially surpasses existing methods in both zero-shot and few-shot benchmarks, as depicted in Figure 1. |
| Researcher Affiliation | Collaboration | Fanfan Ye1,2 , Yiqi Fan2 , Qiaoyong Zhong2 , Shicai Yang2 , Di Xie2 , Jie Song1 , Mingli Song1 1Zhejiang University 2Hikvision Research Institute EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: MFU-Queue Algorithm |
| Open Source Code | No | The paper does not explicitly state that source code for the methodology is provided, nor does it include any links to a code repository. |
| Open Datasets | Yes | We validate VQCounter through comprehensive experiments on two well-established datasets, namely FSC147 [Ranjan et al., 2021] and CARPK [Hsieh et al., 2017]. FSC-147 consists of 6,135 images spanning 89 training, 29 validation, and 29 test classes, with each set containing mutually exclusive classes. CARPK includes 989 training and 459 test images of parking lots captured by overhead drones. |
| Dataset Splits | Yes | FSC-147 consists of 6,135 images spanning 89 training, 29 validation, and 29 test classes, with each set containing mutually exclusive classes. Every image is annotated with at least three visual exemplars. CARPK includes 989 training and 459 test images of parking lots captured by overhead drones. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used, such as GPU models, CPU models, or memory specifications. |
| Software Dependencies | No | The paper mentions using the Adam optimizer but does not provide specific version numbers for any software libraries, frameworks (e.g., PyTorch, TensorFlow), or other dependencies. |
| Experiment Setup | Yes | For training, we use strategies similar to Count GD with the Adam optimizer and train for 30 epochs. |