Data-augmentation for reducing dataset bias in person re-identification

Data-augmentation for reducing dataset bias in person re-identification
复制标题

DOI:
10.1109/avss.2015.7301739
复制
发表时间:
2015-10
期刊:
2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
影响因子:
--
通讯作者:
Niall McLaughlin;J. M. D. Rincón;P. Miller
Niall McLaughlin;J. M. D. Rincón;P. Miller
中科院分区:
其他
文献类型:
--
作者:
Niall McLaughlin;J. M. D. Rincón;P. Miller

文献摘要

被引文献

相似文献

在本文中,我们探索了通过使用数据增强来增加可用数据集的可变性来解决行人重新识别中的数据集偏差问题的方法,并介绍了一种基于改变图像背景的重新识别的新颖的数据增强方法。我们表明,使用数据增强可以提高基于卷积网络的重新识别系统的跨数据集泛化,并且改变图像背景可以产生进一步的改进。
In this paper we explore ways to address the issue of dataset bias in person re-identification by using data augmentation to increase the variability of the available datasets, and we introduce a novel data augmentation method for re-identification based on changing the image background. We show that use of data augmentation can improve the cross-dataset generalisation of convolutional network based re-identification systems, and that changing the image background yields further improvements.