Looking beyond appearances: Synthetic training data for deep CNNs in re identification
Looking beyond appearances: Synthetic training data for deep CNNs in re identification
复制标题
DOI：
10.1016/j.cviu.2017.12.002
复制
发表时间：
2018-02-01
影响因子：
4.5
通讯作者：
Theoharis, Theoharis
中科院分区：
文献类型：
--
作者：
Barbosa, Igor Barros;Cristani, Marco;Theoharis, Theoharis
重新识别通常是通过对受试者的外表进行编码来实现的，这意味着人们不会改变自己的着装。在本文中，我们通过提出一个基于深度卷积神经网络的框架SOMAnet来克服这一限制，该框架还对其他区分方面进行建模，即，人体的结构属性(例如，身高、肥胖、性别)。我们的方法在许多方面是独一无二的。首先，SOMAnet基于先启体系结构，与通常的暹罗框架不同。这节省了昂贵的数据准备(通过摄像头配对图像)，并允许了解网络了解到的内容。其次，也是最值得注意的是，训练数据包括由照片真实感人体生成软件创建的合成100K实例数据集SOMAset。SOMAset将以开放源码许可证发布，以支持重新识别方面的进一步开发。合成数据是获取半真实感图像的一种经济高效的方式(在重新识别时通常不需要完全真实感，因为监视摄像机捕捉低分辨率的轮廓)，同时提供对样本的地面真实的完全控制。因此，定制数据w.r.t.相对容易。近在咫尺的监视场景，例如种族。SOMAnet接受过SOMAset培训，并根据最近的重新识别基准进行了微调，即使是穿着不同的服装也能匹配受试者。
Re-identification is generally carried out by encoding the appearance of a subject in terms of outfit, suggesting scenarios where people do not change their attire. In this paper we overcome this restriction, by proposing a framework based on a deep convolutional neural network, SOMAnet, that additionally models other discriminative aspects, namely, structural attributes of the human figure (e.g. height, obesity, gender). Our method is unique in many respects. First, SOMAnet is based on the Inception architecture, departing from the usual siamese framework. This spares expensive data preparation (pairing images across cameras) and allows the understanding of what the network learned. Second, and most notably, the training data consists of a synthetic 100K instance dataset, SOMAset, created by photorealistic human body generation software. SOMAset will be released with a open source license to enable further developments in re-identification. Synthetic data represents a cost-effective way of acquiring semi -realistic imagery (full realism is usually not required in re-identification since surveillance cameras capture low-resolution silhouettes), while at the same time providing complete control of the samples in terms of ground truth. Thus it is relatively easy to customize the data w.r.t. the surveillance scenario at-hand, e.g. ethnicity. SOMAnet, trained on SOMAset and fine-tuned on recent re-identification benchmarks, matches subjects even with different apparel.