An Iterative unsupervised Person Search Algorithm on Natural Scene Images

摘要

Person search is a challenging task due to the different requirements of annotations between person detection and Re-identification. In general, person search methods use the supervised person Re-identification methods, where abundant identity labels of the bounding boxes are essential. However, most person images are unlabeled in the real-world scenario and it is unpractical to annotate the abundant fine-grained labels for unlabeled images. Obviously, the existing supervised methods are not appropriate with the real-world scenario. Therefore, we propose an unsupervised learning method for person search in this paper, which contacts two parts: one is unsupervised person detection and the other is unsupervised person Re-identification. The experimental results on two well-known datasets, CUHK-SYSU and PRW, indicate that proposed method achieves competitive performance than the state-of-art unsupervised methods. Note that proposed method has greater practical significance even though it does not get the results as good as the general supervised methods.