PurifyNet: A Robust Person Re-Identification Model with Noisy Labels

Mang Ye, Pong Chi YUEN*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

59 Citations (Scopus)


Person re-identification (Re-ID) has been widely studied by learning a discriminative feature representation with a set of well-annotated training data. Existing models usually assume that all the training samples are correctly annotated. However, label noise is unavoidable due to false annotations in large-scale industrial applications. Different from the label noise problem in image classification with abundant samples, the person Re-ID task with label noise usually has very limited annotated samples for each identity. In this paper, we propose a robust deep model, namely PurifyNet, to address this issue. PurifyNet is featured in two aspects: 1) it jointly refines the annotated labels and optimizes the neural networks by progressively adjusting the predicted logits, which reuses the wrong labels rather than simply filtering them; 2) it can simultaneously reduce the negative impact of noisy labels and pay more attention to hard samples with correct labels by developing a hard-aware instance re-weighting strategy. With limited annotated samples for each identity, we demonstrate that hard sample mining is crucial for label corrupted Re-ID task, while it is usually ignored in existing robust deep learning methods. Extensive experiments on three datasets demonstrate the robustness of PurifyNet over the competing methods under various settings. Meanwhile, we show that it consistently improves the unsupervised/video-based Re-ID methods. Code is available at: https://github.com/mangye16/ReID-Label-Noise.

Original languageEnglish
Article number8976262
Pages (from-to)2655-2666
Number of pages12
JournalIEEE Transactions on Information Forensics and Security
Publication statusPublished - 30 Jan 2020

Scopus Subject Areas

  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications

User-Defined Keywords

  • instance re-weighting
  • label noise
  • Person re-identification (Re-ID)
  • robust deep learning


Dive into the research topics of 'PurifyNet: A Robust Person Re-Identification Model with Noisy Labels'. Together they form a unique fingerprint.

Cite this