Open AccessEnhanced multi‐dataset transfer learning method for unsupervised person re‐identification using co‐training strategy
Author(s) -
Xian Yuqiao,
Hu Haifeng
Publication year - 2018
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2018.5103
Subject(s) - computer science , benchmark (surveying) , discriminative model , artificial intelligence , cluster analysis , transfer of learning , convolutional neural network , machine learning , unsupervised learning , identification (biology) , pattern recognition (psychology) , process (computing) , botany , geodesy , biology , geography , operating system
This study proposes progressive unsupervised co‐learning for unsupervised person re‐identification by introducing a co‐training strategy in an iterative training process. The authors’ method adopts an iterative training process to improve transferred models by iterating among clustering, selection, exchange, and fine‐tuning. To solve the problem of transferring representations learned from multiple source datasets, their method utilises multiple convolutional neural network (CNN) models trained on different labelled source datasets by feeding soft labels obtained by clustering on target dataset to each other. The enhanced model can learn more discriminative person representations than the single model trained on multiple datasets. Experimental results on two large‐scale benchmark datasets (i.e. DukeMTMC‐reID and Market‐1501) demonstrate that their method can enhance transferred CNN models by using more source datasets and is competitive to the state‐of‐the‐art methods.