Title | ||
---|---|---|
Unsupervised Person Re-Identification Via Re-Ranking Enhanced Sample-Specific Metric Learning |
Abstract | ||
---|---|---|
Despite of the great progress of image-based person re identification, most existing methods use supervised metric learning to build re -identification models and thus require repeated human effort to annotate sample pairs from non overlapping cameras. In this paper, we propose an unsupervised sample-specific metric learning approach (SSML) to alleviate this problem. Specifically, using samples those are negatives (with a high probability) to the query samples, we train a local metric for each query sample following the max-margin learning theory. Moreover, a KNN intersection re-ranking (KIRR) method is used to further decrease the ambiguity of samples and aggregate the re-identification performance. With experiments on three widely used person re -identification datasets: VIPeR, CUHK01, and PRID, we demonstrate that the proposed approach is simple but effective. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Person Re-identification, Sample-specific Metric Learning, Re-ranking |
Field | DocType | ISSN |
Pattern recognition,Ranking,Computer science,Learning theory,Artificial intelligence,Ambiguity,Machine learning | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Heng Zhao | 1 | 32 | 5.34 |
Zhenjun Han | 2 | 176 | 16.40 |
Zhaoju Li | 3 | 1 | 1.30 |
Fei Qin | 4 | 12 | 4.76 |