Zero-Shot Object Counting
Zero-Shot Object Counting
复制标题
DOI：
10.1109/cvpr52729.2023.01492
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Jingyi Xu;Hieu M. Le;Vu Nguyen;Viresh Ranjan;D. Samaras
中科院分区：
文献类型：
--
作者：
Jingyi Xu;Hieu M. Le;Vu Nguyen;Viresh Ranjan;D. Samaras
与类无关的对象计数旨在计算测试时任意类的对象实例。目前解决这一具有挑战性的问题的方法需要人类注释的样本作为输入，这对于新的类别通常是不可用的，特别是对于自主系统。因此，我们提出了零射击对象计数(ZSC)，这是一种新的设置，在测试期间只有类名可用。这样的计数系统不需要循环中的人工注释员，并且可以自动操作。从一个类名出发，我们提出了一种能够准确识别最优块的方法，并将其用作计数样本。具体地说，我们首先构造一个类原型来选择可能包含感兴趣对象的补丁，即与类相关的补丁。此外，我们还介绍了一个模型，该模型可以定量地衡量任意一个斑块作为计数样本的适合程度。通过将该模型应用于所有候选斑块，我们可以选择最合适的斑块作为样本进行计数。在最近的类无关计数数据集FSC-147上的实验结果验证了该方法的有效性。代码可在https://github.com/cvlabstonybrook/zero-shot-counting.上找到
Class-agnostic object counting aims to count object instances of an arbitrary class at test time. Current methods for this challenging problem 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/cvlabstonybrook/zero-shot-counting.