4.6 Article

PRDP: Person Reidentification With Dirty and Poor Data

期刊

IEEE TRANSACTIONS ON CYBERNETICS
卷 52, 期 10, 页码 11014-11026

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2021.3105970

关键词

Training; Noise measurement; Data models; Task analysis; Training data; Predictive models; Heuristic algorithms; Dirty; metric learning; person reidentification (ReID); poor

资金

  1. National Key Research and Development Program of China [2017YFA0700800]
  2. Natural Science Foundation of China (NSFC) [61876171, 61976203]
  3. Open Project Fund from the Shenzhen Institute of Artificial Intelligence and Robotics for Society [AC01202005015]

向作者/读者索取更多资源

In this article, a novel method is proposed to address the dirty data quality and poor quantity issues in person reidentification, using weighted label correction and feature simulation techniques to improve model performance.
In this article, we propose a novel method to simultaneously solve the data problem of dirty quality and poor quantity for person reidentification (ReID). Dirty quality refers to the wrong labels in image annotations. Poor quantity means that some identities have very few images (FewIDs). Training with these mislabeled data or FewIDs with triplet loss will lead to low generalization performance. To solve the label error problem, we propose a weighted label correction based on cross-entropy (wLCCE) strategy. Specifically, according to the influence range of the wrong labels, we first classify the mislabeled images into point label error and set label error. Then, we propose a weighted triplet loss (WTL) to correct the two label errors, respectively. To alleviate the poor quantity issue, we propose a feature simulation based on autoencoder (FSAE) method to generate some virtual samples for FewID. For the authenticity of the simulated features, we transfer the difference pattern of identities with multiple images (MultIDs) to FewIDs by training an autoencoder (AE)-based simulator. In this way, the FewIDs obtain richer expressions to distinguish from other identities. By dealing with a dirty and poor data problem, we can learn more robust ReID models using the triplet loss. We conduct extensive experiments on two public person ReID datasets: 1) Market-1501 and 2) DukeMTMC-reID, to verify the effectiveness of our approach.

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。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据