Abstract
Domain adaptation and adversarial networks are two main approaches for transfer learning. Domain adaptation methods match the mean values of source and target domains, which requires a very large batch size during training. However, adversarial networks are usually unstable when training. In this paper, we propose a joint method of feature matching and adversarial networks to reduce domain discrepancy and mine domaininvariant features from the local and global aspects. At the same time, our method improves the stability of training. Moreover, the method is embedded into a unified convolutional neural network that can be easily optimized by gradient descent. Experimental results show that our joint method can yield the state-of-the-art results on three common public datasets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
PAN S J, YANG Q. A survey on transfer learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345–1359.
PAN S J, TSANG I W, KWOK J T, et al. Domain adaptation via transfer component analysis [J]. IEEE Transactions on Neural Networks, 2011, 22(2): 199–210.
GONG B, SHI Y, SHA F, et al. Geodesic flow kernel for unsupervised domain adaptation [C]//IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 2066–2073.
LONG M S, CAO Y, WANG J M, et al. Learning transferable features with deep adaptation networks [C]//32nd International Conference on Machine Learning. Lille, France: PMLR, 2015: 97–105.
LONG M S, ZHU H, WANG J M, et al. Unsupervised domain adaptation with residual transfer networks [C]//30th Conference on Neural Information Processing Systems (NIPS 2016). Barcelona, Spain: NIPS, 2016: 136–144.
LONG M S, ZHU H, WANG J M, et al. Deep transfer learning with joint adaptation networks [C]//34th International Conference on Machine Learning. Sydney, Australia: PMLR, 2017: 2208–2217.
GRETTON A, BORGWARDT K M, RASCH M J, et al. A kernel two-sample test [J]. Journal of Machine Learning Research, 2012, 13(3): 723–773.
GANIN Y, USTINOVA E, AJAKAN H, et al. Domainadversarial training of neural networks [J]. Journal of Machine Learning Research, 2016, 17(1): 1–35.
TZENG E, HOFFMAN J, SAENKO K, et al. Adversarial discriminative domain adaptation [C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 7167–7176.
LIU M Y, TUZEL O. Coupled generative adversarial networks [C]//29th Conference on Neural Information Processing Systems (NIPS 2016). Barcelona, Spain: NIPS, 2016: 469–477.
SHEN J, QU Y R, ZHANG WN, et al. Wasserstein distance guided representation learning for domain adaptation [C]//Thirty-Second AAAI Conference on Artificial Intelligence. New Orleans, USA: AAAI, 2018: 4058–4065.
GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets [C]//28th Annual Conference on Neural Information Processing Systems. Montreal, Canada: NIPS, 2014: 2672–2680.
GHIFARY M, KLEIJN W B, ZHANG M J. Domain adaptive neural networks for object recognition [M]. Lecture Notes in Computer Science. Cham, Switzerland: Springer International Publishing Switzerland, 2014: 898–904.
TZENG E, HOFFMAN J, ZHANG N, et al. Deep domain confusion: Maximizing for domain invariance [EB/OL]. [2019-04-23]. https://arxiv.org/pdf/1412.3474v1.pdf.
KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]//26th Annual Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, USA: NIPS, 2012: 1097–1105.
YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks? [C]//28th Annual Conference on Neural Information Processing Systems. Montreal, Canada: NIPS, 2014: 3320–3328.
MA S, FU J L, CHEN W C, et al. DA-GAN: Instancelevel image translation by deep attention generative adversarial networks [C]//IEEE ICVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 5657–5666.
SALIMANS T, GOODFELLOW I, ZAREMBA W, et al. Improved techniques for training GANs [C]//29th Conference on Neural Information Processing Systems (NIPS 2016). Barcelona, Spain: NIPS, 2016: 2234–2242.
ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks [C]//IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 2242–2251.
BOUSMALIS K, TRIGEORGIS G, SILBERMAN N, et al. Domain separation networks [C]//29th Conference on Neural Information Processing Systems (NIPS 2016). Barcelona, Spain: NIPS, 2016: 343–351.
LI C L, CHANG W C, CHENG Y, et al. MMD GAN: Towards deeper understanding of moment matching network [C]//31st Annual Conference on Neural Information Processing Systems (NIPS 2017). Long Beach, CA, USA: NIPS, 2017: 2203–2213.
DZIUGAITE G K, ROY D M, GHAHRAMANI Z. Training generative neural networks via maximum mean discrepancy optimization [C]//31st Conference on Uncertainty in Artificial Intelligence. Amsterdam, the Netherlands: AUAI, 2015: 258–267.
SUN B C, FENG J S, SAENKO K. Return of frustratingly easy domain adaptation [C]//Association for the Advance of Artificial Intelligence Conference. Phoenix, Arizona, USA: AAAI Press, 2016: 2058–2065.
DONAHUE J, JIA Y, VINYALS O, et al. DeCAF: A deep convolutional activation feature for generic visual recognition [C]//31st International Conference on Machine Learning. Beijing, China: ICML, 2014: 647–655.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: the Aerospace Science and Technology Foundation (No. 20115557007), the National Natural Science Foundation of China (No. 61673262), and the Military Science and Technology Foundation of China (No. 18-H863-03-ZT-001-006-06)
Rights and permissions
About this article
Cite this article
Zhong, H., Wang, C., Tuo, H. et al. Transfer Learning Based on Joint Feature Matching and Adversarial Networks. J. Shanghai Jiaotong Univ. (Sci.) 24, 699–705 (2019). https://doi.org/10.1007/s12204-019-2132-0
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12204-019-2132-0