Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2022, Vol. 16 Issue (5) : 165341    https://doi.org/10.1007/s11704-022-1342-z
LETTER
Metric learning for domain adversarial network
Haifeng HU1(), Yan YANG1, Yueming YIN1, Jiansheng WU2
1. College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
2. College of Geography and Biological Information, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
 Download: PDF(651 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Corresponding Author(s): Haifeng HU   
Just Accepted Date: 23 September 2021   Issue Date: 23 February 2022
 Cite this article:   
Haifeng HU,Yan YANG,Yueming YIN, et al. Metric learning for domain adversarial network[J]. Front. Comput. Sci., 2022, 16(5): 165341.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-022-1342-z
https://academic.hep.com.cn/fcs/EN/Y2022/V16/I5/165341
Fig.1  Metric learning for domain adversarial network (ML-DAN)
Method A→W D→W W→D A→D D→A W→A Avg.
Resnet50 68.4 96.7 99.3 68.9 62.5 62.7 76.4
DAN 80.5 97.1 99.6 78.6 63.6 62.8 80.4
DANN 82 96.9 99.1 79.7 68.2 67.4 82.2
ADDA 86.2 96.2 98.4 77.8 69.5 68.9 82.8
JAN 85.4 97.4 99.8 84.7 68.6 70 84.3
MADA 90 97.4 99.6 87.8 70.3 66.4 85.2
MCD 89.6 98.5 100 91.3 69.6 70.8 86.6
CDAN 93.1 98.2 100 89.8 70.1 68 86.6
ML-DAN 93.64 99.05 100 94.56 72.18 71.19 88.44
Tab.1  Accuracy (%) on Office-31 for unsupervised domain adaptation (ResNet-50)
Method Ar→CI Ar→Pr Ar→Rw CI→Ar CI→Pr CI→Rw Pr→Ar Pr→CI Pr→Rw Rw→Ar Rw→CI Rw→Pr Avg.
Resnet50 42.5 50 58 37.4 41.9 46.2 38.5 42.4 60.4 53.9 41.2 59.9 47.7
DAN 43.6 57 67.9 45.8 56.5 60.4 44 43.6 67.7 63.1 51.5 74.3 56.3
DANN 45.6 59.3 70.1 47 58.5 60.9 46.1 43.7 68.5 63.2 51.8 76.8 57.6
JAN 45.9 61.2 68.9 50.4 59.7 61 45.8 43.4 70.3 63.9 52.4 76.8 58.3
CDAN 49 69.3 74.5 54.4 66 68.4 55.6 48.3 75.9 68.4 55.4 80.5 63.8
ML-DAN 56.41 73.17 76.71 61.23 70.27 71.58 60.55 53.54 78.59 69.63 61.4 83.08 68.01
Tab.2  Accuracy (%) on Office-Home for unsupervised domain adaptation (ResNet-50)
1 H Ajakan, P Germain, H Larochelle, F Laviolette, M Marchand. Domain-adversarial neural networks. In: Proceedings of the NIPS 2014 Workshop on Transfer and Multitask learning: Theory Meets Practice. 2014
2 E Tzeng, J Hoffman, K Saenko, T Darrell. Adversarial discriminative domain adaptation. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017, 2962−2971
3 S Ben-David , J Blitzer , K Crammer , A Kulesza , F Pereira , J W Vaughan . A theory of learning from different domains. Machine Learning, 2010, 79( 1): 151– 175
4 M Long, H Zhu, J Wang, M I Jordan. Unsupervised domain adaptation with residual transfer networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 136– 144
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed