Name
Title | ||
|---|---|---|
The devil in the tail: Cluster consolidation plus cluster adaptive balancing loss for unsupervised person re-identification |
Abstract | ||
|---|---|---|
•We propose a simple yet effective approach, called cluster consolidation (CC), to reorganize the clustering result. The reorganization step can improve the compactness of larger clusters by pruning a proportion of unreliable samples into tiny clusters or singletons.•We propose a cluster adaptive balancing (CAB) loss to effectively train the network by automatically assigning proper weights to the imbalanced and noisy pseudo labels. In this way, the unsupervised person Re-ID task is formulated as a cluster adaptive long-tail learning problem.•Extensive experiments on widely used benchmark datasets are conducted and demonstrate state-of-the-art performance. A set of ablation studies are also provided. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1016/j.patcog.2022.108763 | Pattern Recognition |
Keywords | DocType | Volume |
Unsupervised person re-identification,Cluster consolidation,Cluster adaptive balancing loss,Long-tail problem | Journal | 129 |
ISSN | Citations | PageRank |
0031-3203 | 0 | 0.34 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mingkun Li | 1 | 0 | 1.69 |
| He Sun | 2 | 0 | 0.68 |
| Chaoqun Lin | 3 | 0 | 1.35 |
| Chun-Guang Li | 4 | 310 | 17.35 |
| Jun Guo | 5 | 1579 | 137.24 |