Name
Abstract | ||
|---|---|---|
Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of labeled image data from the scenes of interest. When the data to be recognized are different from the source-domain training ones, a number of domain adaptation approaches have been proposed. Nevertheless, one still needs to collect labeled or unlabelled target-domain data during training. In this paper, we tackle an even more challenging and practical setting, domain generalized (DG) person re-ID. That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data. In order to learn domain-invariant features without knowing the target domain of interest, we present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data. The learned features would exhibit sufficient domain-invariant properties while not overfitting the source-domain data or ID labels. Our experiments on four benchmark datasets confirm the superiority of our method over the slate-of-the-arts. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICPR48806.2021.9413013 | 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) |
DocType | ISSN | Citations |
Conference | 1051-4651 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ci-Siang Lin | 1 | 0 | 1.35 |
| Yuan-Chia Cheng | 2 | 0 | 0.34 |
| Yu-Chiang Frank Wang | 3 | 914 | 61.63 |