Generated Data with Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Publication Type:
Journal Article
Citation:
IEEE Signal Processing Letters, 2020, 27 pp. 391 - 395
Issue Date:
2020-01-01
Filename Description Size
Binder1.pdfAccepted Manuscript424.16 kB
Adobe PDF
Full metadata record
© 1994-2012 IEEE. Recently, Generative Adversarial Network (GAN) has been adopted to improve person re-identification (person re-ID) performance through data augmentation. However, directly leveraging generated data to train a re-ID model may easily lead to over-fitting issue on these extra data and decrease the generalisability of model to learn true ID-related features from real data. Inspired by the previous approach which assigns multi-pseudo labels on the generated data to reduce the risk of over-fitting, we propose to take sparse regularization into consideration. We attempt to further improve the performance of current re-ID models by using the unlabeled generated data. The proposed Sparse Regularized Multi-Pseudo Label (SRMpL) can effectively prevent the over-fitting issue when some larger weights are assigned to the generated data. Our experiments are carried out on two publicly available person re-ID datasets (e.g., Market-1501 and DukeMTMC-reID). Compared with existing unlabeled generated data re-ID solutions, our approach achieves competitive performance. Two classical re-ID models are used to verify our sparse regularization label on generated data, i.e., an ID-embedding network and a two-stream network.
Please use this identifier to cite or link to this item: