A Simple-but-Effective Baseline for Training-Free Class-Agnostic Counting

Yuhao Lin, Haiming Xu, Lingqiao Liu, Javen Qinfeng Shi; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 8144-8153

Abstract


Class-Agnostic Counting (CAC) seeks to accurately count objects in a given image with only a few reference examples. While previous methods achieving this relied on additional training recent efforts have shown that it's possible to accomplish this without training by utilizing pre-existing foundation models particularly the Segment Anything Model (SAM) for counting via instance-level segmentation. Although promising current training-free methods still lag behind their training-based counterparts in terms of performance. In this research we present a straightforward training-free solution that effectively bridges this performance gap serving as a strong baseline. The primary contribution of our work lies in the discovery of four key technologies that can enhance performance. Specifically we suggest employing a superpixel algorithm to generate more precise initial point prompts utilizing an image encoder with richer semantic knowledge to replace the SAM encoder for representing candidate objects and adopting a multiscale mechanism and a transductive prototype scheme to update the representation of reference examples. By combining these four technologies our approach achieves significant improvements over existing training-free methods and delivers performance on par with training-based ones.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_WACV, author = {Lin, Yuhao and Xu, Haiming and Liu, Lingqiao and Shi, Javen Qinfeng}, title = {A Simple-but-Effective Baseline for Training-Free Class-Agnostic Counting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8144-8153} }