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:类不可知天体计数的目的是在测试时计数任意类的物体实例。 它具有挑战性, 但也允许许多潜在的应用程序。 目前的方法要求以人类附加说明的示例为输入, 这些输入通常无法用于新分类, 特别是用于自动系统。 因此, 我们提议了零点天体计数( ZSC), 这是一种新设置, 只有类名称在测试时可以使用。 这种计数系统不需要在循环中进行人工识别, 并且可以自动运行。 从一个类名称开始, 我们建议一种方法, 可以准确确定最佳的补丁, 然后可以用作计数Exemplars。 具体地说, 我们首先建立一个分类原型, 选择可能包含相关对象的补丁。 此外, 我们引入了一种模型, 可以量化任意补丁是否适合计数 Exemampl。 通过将这个模型应用到所有候选的补丁, 我们可以选择最合适的补丁作为计数。 在最近一个类、 agnoti计数数据设置上的实验结果, FSC-147, 验证我们的方法的有效性。</s>