Name
Title | ||
|---|---|---|
Person Re-identification with Hierarchical Deep Learning Feature and efficient XQDA Metric. |
Abstract | ||
|---|---|---|
Feature learning and metric learning are two important components in person re-identification (re-id). In this paper, we utilize both aspects to refresh the current State-Of-The-Arts (SOTA). Our solution is based on a classification network with label smoothing regularization (LSR) and multi-branch tree structure. The insight is that some middle network layers are found surprisingly better than the last layers on the re-id task. A Hierarchical Deep Learning Feature (HDLF) is thus proposed by combining such useful middle layers. To learn the best metric for the high-dimensional HDLF, an efficient eXQDA metric is proposed to deal with the large-scale big-data scenarios. The proposed HDLF and eXQDA are evaluated with current SOTA methods on five benchmark datasets. Our methods achieve very high re-id results, which are far beyond state-of-the-art solutions. For example, our approach reaches 81.6%, 96.1% and 95.6% Rank-1 accuracies on the ILIDS-VID, PRID2011 and Market-1501 datasets. Besides, the code and related materials (lists of over 1800 re-id papers and 170 top conference re-id papers) are released for research purposes.
|
Year | DOI | Venue |
|---|---|---|
2018 | 10.1145/3240508.3240717 | MM '18: ACM Multimedia Conference
Seoul
Republic of Korea
October, 2018 |
Keywords | Field | DocType |
Person re-identification, Deep learning, Metric learning | Computer vision,Computer science,Smoothing,Regularization (mathematics),Tree structure,Artificial intelligence,Deep learning,Machine learning,Feature learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-5665-7 | 1 | 0.34 |
References | Authors | |
34 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mingyong Zeng | 1 | 2 | 1.84 |
| Chang Tian | 2 | 105 | 19.53 |
| Zemin Wu | 3 | 14 | 1.51 |