论文标题
示例免费的不可知论计数
Exemplar Free Class Agnostic Counting
论文作者
论文摘要
我们解决了不可知论计数的任务，该任务旨在在测试时间内对象在新颖对象类别中进行对象，而无需访问该类别的标记培训数据。所有以前的不可知论计数方法无法在全自动设置中起作用，并且需要计算昂贵的测试时间适应。为了应对这些挑战，我们提出了一个视觉计数器，该视觉计数器在完全自动化的设置中运行，不需要任何测试时间适应。我们提出的方法首先从图像中重复对象来标识示例，然后计算重复对象。我们提出了一个新的区域建议网络，用于识别示例。在识别示例后，我们通过使用基于密度估计的视觉计数器获得相应的计数。我们在FSC-147数据集上评估了我们提出的方法，并表明与现有方法相比，它的性能优越。
We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a fully automated setting, and require computationally expensive test time adaptation. To address these challenges, we propose a visual counter which operates in a fully automated setting and does not require any test time adaptation. Our proposed approach first identifies exemplars from repeating objects in an image, and then counts the repeating objects. We propose a novel region proposal network for identifying the exemplars. After identifying the exemplars, we obtain the corresponding count by using a density estimation based Visual Counter. We evaluate our proposed approach on FSC-147 dataset, and show that it achieves superior performance compared to the existing approaches.
