Vicinal Counting Networks
Vicinal Counting Networks
复制标题
DOI：
10.1109/cvprw56347.2022.00467
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Viresh Ranjan;Minh Hoai
中科院分区：
文献类型：
--
作者：
Viresh Ranjan;Minh Hoai
我们解决了少枪计数的任务。给定一个包含多个新视觉类别的对象和几个描述感兴趣视觉类别的示例边界框的图像，我们希望对图像中所需视觉类别的所有实例进行计数。构建精确的少数镜头视觉计数器的一个关键挑战是由于收集和注释数据所需的艰苦工作而导致注释的训练数据稀缺。为了应对这一挑战，我们提出了邻近计数网络，它学习增加现有的训练数据沿着学习计数。邻位计数网络由一个生成器和一个计数网络组成。该生成器将图像沿着随机噪声矢量作为输入，并生成输入图像的增强版本。计数网络学习对原始图像和增强图像中的对象进行计数。生成器的训练信号来自计数网络的计数损失，并且生成器旨在合成导致小计数损失的图像。与在对抗环境中训练的GAN不同，邻近计数网络是在合作环境中训练的，生成器旨在帮助计数网络实现对合成图像的准确预测。我们还表明，我们提出的数据增强框架可以扩展到其他计数任务，如人群计数。
We tackle the task of Few-Shot Counting. Given an image containing multiple objects of a novel visual category and few exemplar bounding boxes depicting the visual category of interest, we want to count all of the instances of the desired visual category in the image. A key challenge in building an accurate few-shot visual counter is the scarcity of annotated training data due to the laborious effort needed for collecting and annotating the data. To address this challenge, we propose Vicinal Counting Networks, which learn to augment the existing training data along with learning to count. A Vicinal Counting Network consists of a generator and a counting network. The generator takes as input an image along with a random noise vector and generates an augmented version of the input image. The counting network learns to count the objects in the original and augmented images. The training signal for the generator comes from the counting loss of the counting network, and the generator aims to synthesize images which result in a small counting loss. Unlike GANs which are trained in an adversarial setting, Vicinal Counting Networks are trained in a cooperative setting where the generator aims to help the counting network in achieving accurate predictions on the synthesized images. We also show that our proposed data augmentation framework can be extended to other counting tasks like crowd counting.