|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM292578245 |
| 003 |
DE-627 |
| 005 |
20240229162111.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2019 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2019.2891895
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1308.xml
|
| 035 |
|
|
|a (DE-627)NLM292578245
|
| 035 |
|
|
|a (NLM)30629502
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wu, Yu
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Progressive Learning for Person Re-Identification with One Example
|
| 264 |
|
1 |
|c 2019
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 27.02.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status Publisher
|
| 520 |
|
|
|a In this paper, we focus on the one-example person re-identification (re-ID) task, where each identity has only one labeled example along with many unlabeled examples. We propose a progressive framework which gradually exploits the unlabeled data for person re-ID. In this framework, we iteratively (1) update the Convolutional Neural Network (CNN) model and (2) estimate pseudo labels for the unlabeled data. We split the training data into three parts, i.e., labeled data, pseudo-labeled data, and indexlabeled data. Initially, the re-ID model is trained using the labeled data. For the subsequent model training, we update the CNN model by the joint training on the three data parts. The proposed joint training method can optimize the model by both the data with labels (or pseudo labels) and the data without any reliable labels. For the label estimation step, instead of using a static sampling strategy, we propose a progressive sampling strategy to increase the number of the selected pseudo-labeled candidates step by step. We select a few candidates with most reliable pseudo labels from unlabeled examples as the pseudo-labeled data, and keep the rest as index-labeled data by assigning them with the data indexes. During iterations, the index-labeled data are dynamically transferred to pseudo-labeled data. Notably, the rank-1 accuracy of our method outperforms the state-of-the-art method by 21.6 points (absolute, i.e., 62.8% vs. 41.2%) on MARS, and 16.6 points on DukeMTMC-VideoReID. Extended to the few-example setting, our approach with only 20% labeled data surprisingly achieves comparable performance to the supervised state-of-the-art method with 100% labeled data
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lin, Yutian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Dong, Xuanyi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yan, Yan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bian, Wei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Yi
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g (2019) vom: 10. Jan.
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g year:2019
|g day:10
|g month:01
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2019.2891895
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|j 2019
|b 10
|c 01
|