期刊
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 1470-1478出版社
IEEE
DOI: 10.1109/CVPR.2018.00159
关键词
-
资金
- National Key RAMP
- D Program of China [2017YFB1002202]
- National Natural Science Foundation of China [61471273, 61771348]
- Wuhan Morning Light Plan of Youth Science and Technology [2017050304010302]
- LIESMARS Special Research Funding
In this paper, a novel deep architecture named Braid-Net is proposed for person re-identification. BraidNet has a specially designed WConv layer, and the cascaded WConv structure learns to extract the comparison features of two images, which are robust to misalignments and color differences across cameras. Furthermore, a Channel Scaling layer is designed to optimize the scaling factor of each input channel, which helps mitigate the zero gradient problem in the training phase. To solve the problem of imbalanced volume of negative and positive training samples, a Sample Rate Learning strategy is proposed to adaptively update the ratio between positive and negative samples in each batch. Experiments conducted on CUHK03-Detected, CUHK03-Labeled, CUHK01, Market-1501 and DukeMTMC-reID datasets demonstrate that our method achieves competitive performance when compared to state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据