Back to Search
Start Over
Two-Branch Asymmetric Model With Alternately Clustering for Unsupervised Person Re-Identification
- Source :
- IEEE Signal Processing Letters. 29:75-79
- Publication Year :
- 2022
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2022.
-
Abstract
- In the field of unsupervised person re-identification (Re-ID), mainstream methods adopt cluster algorithm to generate pseudo labels for training. Despite the effectiveness, the cluster algorithm generates noisy labels, which are retained in further model updating and hinder higher performance. To solve this problem, we propose a Two-branch Asymmetric Model with Alternately Clustering. Specifically, the designed Alternately Clustering (AC) strategy leverages a two-branch model to cluster different pseudo labels for each branch, which prevents the continuous existence of identical noisy labels. To establish a mapping between the two label sets, pseudo label mapping constraint (PLMC) module is devised, which helps retain reliable pseudo labels. Our method improves the quality of generated pseudo labels by keeping noisy labels changing and retaining the reliable ones. Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods.
- Subjects :
- business.industry
Computer science
Applied Mathematics
Pattern recognition
Field (computer science)
Re identification
Cluster algorithm
Constraint (information theory)
ComputingMethodologies_PATTERNRECOGNITION
Signal Processing
Cluster (physics)
Artificial intelligence
Electrical and Electronic Engineering
Cluster analysis
business
Subjects
Details
- ISSN :
- 15582361 and 10709908
- Volume :
- 29
- Database :
- OpenAIRE
- Journal :
- IEEE Signal Processing Letters
- Accession number :
- edsair.doi...........c31bd6ce4b9b8dc8d03e19ca77cdeb25