当前位置: X-MOL 学术Concurr. Comput. Pract. Exp. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Self-training with one-shot stepwise learning method for person re-identification
Concurrency and Computation: Practice and Experience ( IF 1.5 ) Pub Date : 2021-04-05 , DOI: 10.1002/cpe.6296
Daoxun Xia 1, 2 , Haojie Liu 1, 2 , Lili Xu 1 , Jiawen Li 3 , Linna Wang 1
Affiliation  

Person re-identification (Re-ID) aims at identifying the same person across multiple non-overlapping camera views. A number of existing methods have been presented for this task in a fully-supervised manner that requires a large amount of training annotations. However, obtaining high quality labels is extremely time consuming and expensive. In this article, we focus on the semi-supervised person Re-ID and propose a one-shot stepwise learning method to address the above issue. It exploits only one labeled data along with additional unlabeled samples to gradually but steadily improving the discriminative capability of the feature representation. Specifically, we first construct labeled data portion to train Re-ID model. Then we fine-tune the overall system by the following two steps iteratively: (1) assigning the estimated labels to the unlabeled portion; (2) updating the network parameters according to the selected data. During the propagation process, different from conventional sampling method, we propose a novel dynamic sampling strategy to enlarge the pseudo-labeled subset step by step to make the pseudo labels more reliable. On Market-1501, DukeMTMC-ReID and MARS datasets, we conducted extensively experiments to demonstrate that our proposed method contributes indispensably and achieves a very competitive Re-ID performance.

中文翻译:

使用一次性逐步学习方法进行自我重新识别的自我训练

人员重新识别 (Re-ID) 旨在跨多个非重叠摄像机视图识别同一个人。已经以需要大量训练注释的全监督方式为该任务提出了许多现有方法。然而,获得高质量的标签极其耗时且昂贵。在本文中,我们专注于半监督人 Re-ID,并提出了一种一次性逐步学习方法来解决上述问题。它仅利用一个标记数据和额外的未标记样本来逐步但稳定地提高特征表示的判别能力。具体来说,我们首先构造标记数据部分来训练 Re-ID 模型。然后我们通过以下两个步骤迭代地微调整个系统:(1) 将估计的标签分配给未标记的部分;(2)根据选择的数据更新网络参数。在传播过程中,与传统的采样方法不同,我们提出了一种新颖的动态采样策略,逐步扩大伪标签子集,使伪标签更加可靠。在 Market-1501、DukeMTMC-ReID 和 MARS 数据集上,我们进行了广泛的实验,以证明我们提出的方法不可或缺,并实现了非常有竞争力的 Re-ID 性能。
更新日期:2021-04-05
down
wechat
bug