Deep adversarial domain adaptation network
The advantage of adversarial domain adaptation is that it uses the idea of adversarial adaptation to confuse the feature distribution of two domains and solve the problem of domain transfer in transfer learning. However, although the discriminator completely confuses the two domains, adversarial dom...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2020-10-01
|
| Series: | International Journal of Advanced Robotic Systems |
| Online Access: | https://doi.org/10.1177/1729881420964648 |
| _version_ | 1818429060799266816 |
|---|---|
| author | Lan Wu Chongyang Li Qiliang Chen Binquan Li |
| author_facet | Lan Wu Chongyang Li Qiliang Chen Binquan Li |
| author_sort | Lan Wu |
| collection | DOAJ |
| description | The advantage of adversarial domain adaptation is that it uses the idea of adversarial adaptation to confuse the feature distribution of two domains and solve the problem of domain transfer in transfer learning. However, although the discriminator completely confuses the two domains, adversarial domain adaptation still cannot guarantee the consistent feature distribution of the two domains, which may further deteriorate the recognition accuracy. Therefore, in this article, we propose a deep adversarial domain adaptation network, which optimises the feature distribution of the two confused domains by adding multi-kernel maximum mean discrepancy to the feature layer and designing a new loss function to ensure good recognition accuracy. In the last part, some simulation results based on the Office-31 and Underwater data sets show that the deep adversarial domain adaptation network can optimise the feature distribution and promote positive transfer, thus improving the classification accuracy. |
| first_indexed | 2024-12-14T15:11:31Z |
| format | Article |
| id | doaj.art-ad737d8138614ec8936ae6100eccb8e1 |
| institution | Directory Open Access Journal |
| issn | 1729-8814 |
| language | English |
| last_indexed | 2024-12-14T15:11:31Z |
| publishDate | 2020-10-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Advanced Robotic Systems |
| spelling | doaj.art-ad737d8138614ec8936ae6100eccb8e12022-12-21T22:56:32ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142020-10-011710.1177/1729881420964648Deep adversarial domain adaptation networkLan Wu0Chongyang Li1Qiliang Chen2Binquan Li3 School of Electrical Engineering, , Zhengzhou, China School of Electrical Engineering, , Zhengzhou, China Beijing Microelectronics Technology Institute, Beijing, China School of Electrical Engineering, , Zhengzhou, ChinaThe advantage of adversarial domain adaptation is that it uses the idea of adversarial adaptation to confuse the feature distribution of two domains and solve the problem of domain transfer in transfer learning. However, although the discriminator completely confuses the two domains, adversarial domain adaptation still cannot guarantee the consistent feature distribution of the two domains, which may further deteriorate the recognition accuracy. Therefore, in this article, we propose a deep adversarial domain adaptation network, which optimises the feature distribution of the two confused domains by adding multi-kernel maximum mean discrepancy to the feature layer and designing a new loss function to ensure good recognition accuracy. In the last part, some simulation results based on the Office-31 and Underwater data sets show that the deep adversarial domain adaptation network can optimise the feature distribution and promote positive transfer, thus improving the classification accuracy.https://doi.org/10.1177/1729881420964648 |
| spellingShingle | Lan Wu Chongyang Li Qiliang Chen Binquan Li Deep adversarial domain adaptation network International Journal of Advanced Robotic Systems |
| title | Deep adversarial domain adaptation network |
| title_full | Deep adversarial domain adaptation network |
| title_fullStr | Deep adversarial domain adaptation network |
| title_full_unstemmed | Deep adversarial domain adaptation network |
| title_short | Deep adversarial domain adaptation network |
| title_sort | deep adversarial domain adaptation network |
| url | https://doi.org/10.1177/1729881420964648 |
| work_keys_str_mv | AT lanwu deepadversarialdomainadaptationnetwork AT chongyangli deepadversarialdomainadaptationnetwork AT qiliangchen deepadversarialdomainadaptationnetwork AT binquanli deepadversarialdomainadaptationnetwork |