GAN-based unsupervised domain adaptive person re-identification
Aiming at the problem that the inaccurate clustering in the unsupervised domain adaptive pedestrian re-recognition results in low network recognition accuracy, an unsupervised domain adaptive pedestrian re-recognition method based on generative confrontation network was proposed.Firstly, the CNN mod...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2021-02-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021016/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529088955645952 |
|---|---|
| author | Shengsheng ZHENG Haibing YIN Xiaofeng HUANG Tianjie ZHANG |
| author_facet | Shengsheng ZHENG Haibing YIN Xiaofeng HUANG Tianjie ZHANG |
| author_sort | Shengsheng ZHENG |
| collection | DOAJ |
| description | Aiming at the problem that the inaccurate clustering in the unsupervised domain adaptive pedestrian re-recognition results in low network recognition accuracy, an unsupervised domain adaptive pedestrian re-recognition method based on generative confrontation network was proposed.Firstly, the CNN model was optimized by using the batch normalization layer after the pooling layer, deleting a fully connected layer and adopting the Adam optimizer.Secondly, the cluster error was analyzed and the important parameter in the cluster was decided based on minimum error rate Bayesian decision theory.Finally, the generative adversarial network was utilized to adjust the cluster.These steps effectively improved the recognition accuracy of unsupervised domain adaptive person re-identification.In the case of the source domain Market-1501 and the target domain DukeMTMC-reID, experimental results show that mAP and Rank-1 can reach 53.7% and 71.6%, respectively. |
| format | Article |
| id | doaj-art-594a00b09f7949aaa67ed5a44f41b141 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2021-02-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-594a00b09f7949aaa67ed5a44f41b1412025-01-15T03:25:52ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012021-02-01379910659806785GAN-based unsupervised domain adaptive person re-identificationShengsheng ZHENGHaibing YINXiaofeng HUANGTianjie ZHANGAiming at the problem that the inaccurate clustering in the unsupervised domain adaptive pedestrian re-recognition results in low network recognition accuracy, an unsupervised domain adaptive pedestrian re-recognition method based on generative confrontation network was proposed.Firstly, the CNN model was optimized by using the batch normalization layer after the pooling layer, deleting a fully connected layer and adopting the Adam optimizer.Secondly, the cluster error was analyzed and the important parameter in the cluster was decided based on minimum error rate Bayesian decision theory.Finally, the generative adversarial network was utilized to adjust the cluster.These steps effectively improved the recognition accuracy of unsupervised domain adaptive person re-identification.In the case of the source domain Market-1501 and the target domain DukeMTMC-reID, experimental results show that mAP and Rank-1 can reach 53.7% and 71.6%, respectively.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021016/unsupervised domain adaptiveperson re-identificationgenerative adversarial network |
| spellingShingle | Shengsheng ZHENG Haibing YIN Xiaofeng HUANG Tianjie ZHANG GAN-based unsupervised domain adaptive person re-identification Dianxin kexue unsupervised domain adaptive person re-identification generative adversarial network |
| title | GAN-based unsupervised domain adaptive person re-identification |
| title_full | GAN-based unsupervised domain adaptive person re-identification |
| title_fullStr | GAN-based unsupervised domain adaptive person re-identification |
| title_full_unstemmed | GAN-based unsupervised domain adaptive person re-identification |
| title_short | GAN-based unsupervised domain adaptive person re-identification |
| title_sort | gan based unsupervised domain adaptive person re identification |
| topic | unsupervised domain adaptive person re-identification generative adversarial network |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021016/ |
| work_keys_str_mv | AT shengshengzheng ganbasedunsuperviseddomainadaptivepersonreidentification AT haibingyin ganbasedunsuperviseddomainadaptivepersonreidentification AT xiaofenghuang ganbasedunsuperviseddomainadaptivepersonreidentification AT tianjiezhang ganbasedunsuperviseddomainadaptivepersonreidentification |