Crowd Counting with Minimal Data Using Generative Adversarial Networks for Multiple Target Regression
Crowd Counting with Minimal Data Using Generative Adversarial Networks for Multiple Target Regression
复制标题
DOI：
10.1109/wacv.2018.00131
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Greg Olmschenk;Hao Tang;Zhigang Zhu
中科院分区：
文献类型：
--
作者：
Greg Olmschenk;Hao Tang;Zhigang Zhu
在这项工作中，我们使用生成对抗网络（GAN）来训练使用最小数据的人群计数网络。我们描述了如何修改GAN目标，以允许在半监督学习中使用未标记数据来进行推理训练。更一般地说，我们解释了这些相同的方法如何用于更一般的多元回归目标半监督学习，人群计数是一个示范示例。给定一个卷积神经网络（CNN），其功能相当于GAN中的鉴别器，我们提供的实验结果表明，即使CNN可以访问更多的标记数据，我们的GAN也能够优于CNN。这显示了用少量数据训练这种网络以达到高精度的潜力。我们的主要目标不是在整个数据集上使用改进的方法超越最先进的技术，而是通过半监督学习，我们可以将训练推理网络所需的数据减少到给定的精度。为此，用不同数量的图像和摄像机进行了系统的实验，以显示在哪些情况下半监督gan可以改善结果。
In this work, we use a generative adversarial network (GAN) to train crowd counting networks using minimal data. We describe how GAN objectives can be modified to allow for the use of unlabeled data to benefit inference training in semi-supervised learning. More generally, we explain how these same methods can be used in more generic multiple regression target semi-supervised learning, with crowd counting being a demonstrative example. Given a convolutional neural network (CNN) with capabilities equivalent to the discriminator in the GAN, we provide experimental results which show that our GAN is able to outperform the CNN even when the CNN has access to significantly more labeled data. This presents the potential of training such networks to high accuracy with little data. Our primary goal is not to outpreform the state-of-the-art using an improved method on the entire dataset, but instead we work to show that through semi-supervised learning we can reduce the data required to train an inference network to a given accuracy. To this end, systematic experiments are performed with various numbers of images and cameras to show under which situations the semi-supervised GANs can improve results.