1. Pro-ReID: Producing reliable pseudo labels for unsupervised person re-identification.
- Author
-
Sun, Haiming and Ma, Shiwei
- Subjects
- *
GAUSSIAN mixture models , *TASK performance , *DATA distribution , *PRIOR learning , *THIRD parties (Law) - Abstract
Mainstream unsupervised person ReIDentification (ReID) is on the basis of the alternation of clustering and fine-tuning to promote the task performance, but the clustering process inevitably produces noisy pseudo labels, which seriously constrains the further advancement of the task performance. To conquer the above concerns, the novel Pro-ReID framework is proposed to produce reliable person samples from the pseudo-labeled dataset to learn feature representations in this work. It consists of two modules: Pseudo Labels Correction (PLC) and Pseudo Labels Selection (PLS). Specifically, we further leverage the temporal ensemble prior knowledge to promote task performance. The PLC module assigns corresponding soft pseudo labels to each sample with control of soft pseudo label participation to potentially correct for noisy pseudo labels generated during clustering; the PLS module associates the predictions of the temporal ensemble model with pseudo label annotations and it detects noisy pseudo labele examples as out-of-distribution examples through the Gaussian Mixture Model (GMM) to supply reliable pseudo labels for the unsupervised person ReID task in consideration of their loss data distribution. Experimental findings validated on three person (Market-1501, DukeMTMC-reID and MSMT17) and one vehicle (VeRi-776) ReID benchmark establish that the novel Pro-ReID framework achieves competitive performance, in particular the mAP on the ambitious MSMT17 that is 4.3% superior to the state-of-the-art methods. • The PLC module is designed to produce soft pseudo labels that contain more person category information, as a way to potentially correct noisy pseudo labels and mitigate their negative influence on the training of the model. • The PLS module is modeling the predicted loss values of temporal ensemble models utilizing the GMM to identify noisy pseudo label samples as out-of-distribution samples, which is employed to select reliable samples for the unsupervised person ReID task. • Experimental results validated on three benchmark datasets demonstrate the competitive performance of the Pro-ReID framework. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF