Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often unavailable for novel categories, especially for autonomous systems. Thus, we propose zero-shot object counting (ZSC), a new setting where only the class name is available during test time. Such a counting system does not require human annotators in the loop and can operate automatically. Starting from a class name, we propose a method that can accurately identify the optimal patches which can then be used as counting exemplars. Specifically, we first construct a class prototype to select the patches that are likely to contain the objects of interest, namely class-relevant patches. Furthermore, we introduce a model that can quantitatively measure how suitable an arbitrary patch is as a counting exemplar. By applying this model to all the candidate patches, we can select the most suitable patches as exemplars for counting. Experimental results on a recent class-agnostic counting dataset, FSC-147, validate the effectiveness of our method. Code is available at https://github.com/cvlab-stonybrook/zero-shot-counting

翻译：类别无关目标计数旨在测试时对任意类别的目标实例进行计数。该任务虽具挑战性，却能赋能众多潜在应用。现有方法需依赖人工标注的示例作为输入，而对于新类别（尤其是自主系统场景中的新类别）此类示例往往难以获取。为此，我们提出零样本目标计数（ZSC）这一新设定——测试时仅需提供类别名称。此类计数系统无需人工标注参与，可全自动运行。基于类别名称，我们提出一种方法，能够精准识别最优图像块，并将其用作计数示例。具体而言：首先构建类别原型以筛选可能包含感兴趣目标的图像块（即类别相关块）；进而引入一个能定量评估任意图像块作为计数示例适用性的模型。将该模型应用于所有候选块后，即可选取最优块作为计数示例。在最新类别无关计数数据集FSC-147上的实验结果验证了本方法的有效性。代码已开源至https://github.com/cvlab-stonybrook/zero-shot-counting