Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at \url{https://github.com/Vision-Intelligence-and-Robots-Group/count-anything}.
翻译：最近，Meta AI发布了Segment Anything 模型（SAM），由于其在类别无关分割方面的出色性能，引起了人们的关注。在这项研究中，我们探讨了将SAM用于少样本目标计数的挑战性任务，该任务涉及通过提供一些示例的边界框来计数一个未知类别的对象。我们将SAM的性能与其他少样本计数方法进行比较，并发现其目前的性能不令人满意，特别是对于小型和拥挤的物体。代码可在 \url{https://github.com/Vision-Intelligence-and-Robots-Group/count-anything} 找到。
相关内容
微信扫码咨询专知VIP会员