Hard Samples Rectification for Unsupervised Cross-domain Person
Re-identification
- URL: http://arxiv.org/abs/2106.07204v1
- Date: Mon, 14 Jun 2021 07:38:42 GMT
- Title: Hard Samples Rectification for Unsupervised Cross-domain Person
Re-identification
- Authors: Chih-Ting Liu, Man-Yu Lee, Tsai-Shien Chen, Shao-Yi Chien
- Abstract summary: We propose a Hard Samples Rectification learning scheme which resolves the weakness of original clustering-based methods.
Our HSR contains two parts, an inter-camera mining method that helps recognize a person under different views (hard positive) and a part-based homogeneity technique that makes the model discriminate different persons but with similar appearance (hard negative)
By rectifying those two hard cases, the re-ID model can learn effectively and achieve promising results on two large-scale benchmarks.
- Score: 29.293741858274146
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Person re-identification (re-ID) has received great success with the
supervised learning methods. However, the task of unsupervised cross-domain
re-ID is still challenging. In this paper, we propose a Hard Samples
Rectification (HSR) learning scheme which resolves the weakness of original
clustering-based methods being vulnerable to the hard positive and negative
samples in the target unlabelled dataset. Our HSR contains two parts, an
inter-camera mining method that helps recognize a person under different views
(hard positive) and a part-based homogeneity technique that makes the model
discriminate different persons but with similar appearance (hard negative). By
rectifying those two hard cases, the re-ID model can learn effectively and
achieve promising results on two large-scale benchmarks.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.