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

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on information forensics and security 2020, Vol.15, p.2655-2666
Main Authors: Ye, Mang, Yuen, Pong C.
Format: Article
Language:English
Subjects:
Annotations
Deep learning
Image classification
Industrial applications
instance re-weighting
label noise
Labels
Machine learning
Neural networks
Noise
Noise measurement
Person re-identification (Re-ID)
robust deep learning
Robustness
Task analysis
Training
Training data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1556-6013
1556-6021
DOI:10.1109/TIFS.2020.2970590