arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.01035cs.CV
收藏

IAUnet:用于人员重新识别的全局上下文感知特征学习

IAUnet: Global Context-Aware Feature Learning for Person Re-Identification

Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS(中国科学院计算技术研究所智能信息处理重点实验室);University of Chinese Academy of Sciences(中国科学院大学);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)

Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen

摘要:

近年来,基于CNN网络的人员重新识别(reID)取得了良好的性能。然而,大多数现有的基于CNN的方法没有充分利用时空上下文建模。事实上,全局时空背景可以极大地澄清局部干扰,以增强目标特征表示。为了全面利用时空上下文信息,在这项工作中,我们提出了一个新的块,交互聚合更新(IAU),高性能的人reID。首先介绍了时空IAU(STIAU)模块。STIAU将两种类型的上下文交互结合到用于目标特征学习的CNN框架中。在这里,空间交互学习计算单个帧的不同身体部位之间的上下文依赖性。而时间交互用于捕获跨所有帧的相同身体部位之间的上下文依赖性。此外,通道IAU(CIAU)模块的设计,以模拟通道功能之间的语义上下文的相互作用,以提高特征表示,特别是小规模的视觉线索和身体部位。因此,IAU块使该特征能够结合全局空间、时间和信道上下文。它是轻量级的,端到端可训练的,并且可以很容易地插入到现有的CNN中以形成IAUnet。实验表明,IAUnet在图像和视频reID任务上表现良好,并在一般对象分类任务上取得了令人信服的结果。源代码可在https://github.com/blue-blue272/ImgReID-IAnet上获得。

英文摘要:

Person re-identification (reID) by CNNs based networks has achieved favorable performance in recent years. However, most of existing CNNs based methods do not take full advantage of spatial-temporal context modeling. In fact, the global spatial-temporal context can greatly clarify local distractions to enhance the target feature representation. To comprehensively leverage the spatial-temporal context information, in this work, we present a novel block, Interaction-Aggregation-Update (IAU), for high-performance person reID. Firstly, Spatial-Temporal IAU (STIAU) module is introduced. STIAU jointly incorporates two types of contextual interactions into a CNN framework for target feature learning. Here the spatial interactions learn to compute the contextual dependencies between different body parts of a single frame. While the temporal interactions are used to capture the contextual dependencies between the same body parts across all frames. Furthermore, a Channel IAU (CIAU) module is designed to model the semantic contextual interactions between channel features to enhance the feature representation, especially for small-scale visual cues and body parts. Therefore, the IAU block enables the feature to incorporate the globally spatial, temporal, and channel context. It is lightweight, end-to-end trainable, and can be easily plugged into existing CNNs to form IAUnet. The experiments show that IAUnet performs favorably against state-of-the-art on both image and video reID tasks and achieves compelling results on a general object categorization task. The source code is available at https://github.com/blue-blue272/ImgReID-IAnet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑