Paper Info
Title
Efficiency-enhanced Progressive Sampling Method on One-shot Person Re-Identification
Abstract
Label estimation on unlabeled samples has become a typical method in one-shot Person Re-Identification. Many existing methods take this form of data augmentation to create the conditions for fully supervised learning. The state-of-theart method uses a cross-iterative mode and achieves huge performance improvement. However, the learning efficiency is very low in this mode. In this paper, we first propose an exponential sampling curve to further explore the relations between sampling number and the performance of the model in each iteration. We found that expanding a proper amount of pseudo-label samples for training can accelerate the growth of performance at the risk of losing final performance. To avoid performance loss, an efficiency-enhanced progressive sampling method is proposed subsequently to expanding sampling number in each iteration by amplification factor and increment factor. Our method not only makes full use of more pseudo-label samples, but also avoids adding too many mislabeled samples at the beginning. Our method is validated on DukeMTMCVideoReID dataset, with the results that our method has a performance comparable to the state-of-the-art method and reduces the number of training iterations by 30% to obtain the best performance.
Year
DOI
Venue
2020
10.1109/RCAR49640.2020.9303302
2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)
Keywords
DocType
ISBN
efficiency-enhanced progressive sampling method,fully supervised learning,cross-iterative mode,learning efficiency,exponential sampling curve,sampling number,one-shot person reidentification,DukeMTMCVideoReID dataset,label estimation,amplification factor,increment factor
Conference
978-1-7281-7294-1
Citations 
PageRank 
References 
0
0.34
6
Authors
5
Name
Order
Citations
PageRank
Jing Zhao101.35
Tang Yuhua235.89
Mingliang Yang300.34
Wanrong Huang401.35
Qiong Yang500.34