MS-DIAL: Multi-Source Domain Alignment Layers for Unsupervised Domain Adaptation
Resumo
In general, deep neural networks trained on a given labeled dataset are expected to produce equivalent results when tested on a new unlabeled dataset. However, data are generally collected by different devices or under varying conditions and thus they often are not part of a same domain, yielding poor results. This is due to the domain shift between data distributions and has been the goal of a research area known as unsupervised domain adaptation. Many prior works have been designed to transfer knowledge between two domains: one source to one target. Since data may be taken from different sources and with different distributions, multi-source domain adaptation has received increasing attention. This paper presents the Multi-Source DomaIn Alignment Layers (MS-DIAL), which reduce the domain shift between multiple sources and a given target by embedding domain alignment layers in any given network. Except for the embedded layers, all the other network parameters are shared among all domains, saving processing time and memory usage. Experiments were performed on digit and object recognition tasks with five public datasets widely used to evaluate domain adaptation methods. Results show that the proposed method is promising and outperforms state-of-the-art approaches.
Referências
H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Panchanathan, "Deep hashing network for unsupervised domain adaptation," in CVPR, 2017, pp. 5385–5394.
F. M. Carlucci, L. Porzi, B. Caputo, E. Ricci, and S. R. Buló, "Just DIAL: domain alignment layers for unsupervised domain adaptation," in Int. Conf. Image Analysis and Processing, 2017, pp. 357–369.
R. Xu, Z. Chen, W. Zuo, J. Yan, and L. Lin, "Deep cocktail network: Multi-source unsupervised domain adaptation with category shift," in CVPR, 2018, pp. 3964–3973.
S. Zhao, B. Li, X. Yue, P. Xu, and K. Keutzer, "MADAN: multi-source adversarial domain aggregation network for domain adaptation," CoRR, vol. abs/2003.00820, 2020.
J. Wen, R. Greiner, and D. Schuurmans, "Domain aggregation networks for multi-source domain adaptation," in ICML, 2020, pp. 10 927–10 937.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278– 2324, 1998.
Y. Ganin and V. S. Lempitsky, "Unsupervised domain adaptation by backpropagation," in ICML, 2015, pp. 1180–1189.
Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, "Reading digits in natural images with unsupervised feature learning," in NIPS Work. Deep Learning and Unsupervised Feature Learning, 2011.
Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. S. Lempitsky, "Domain-adversarial training of neural networks," JMLR, vol. 17, pp. 59:1–59:35, 2016.
S. J. Pan, I. W. Tsang, J. T. Kwok, and Q. Yang, "Domain adaptation via transfer component analysis," IEEE Trans. Neural Networks, vol. 22, no. 2, pp. 199–210, 2011.
M. Baktashmotlagh, M. T. Harandi, and M. Salzmann, "Distribution- matching embedding for visual domain adaptation," JMLR, vol. 17, pp. 108:1–108:30, 2016.
H. Yan, Y. Ding, P. Li, Q. Wang, Y. Xu, and W. Zuo, "Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation," in CVPR, 2017, pp. 945–954.
F. M. Carlucci, L. Porzi, B. Caputo, E. Ricci, and S. R. Buló, "Autodial: Automatic domain alignment layers," in ICCV, 2017, pp. 5077–5085.
X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang, "Moment matching for multi-source domain adaptation," in ICCV, 2019, pp. 1406–1415.
Y. Li, M. Murias, G. Dawson, and D. E. Carlson, "Extracting relationships by multi-domain matching," in NeurIPS, 2018, pp. 6799–6810.
H. Zhao, S. Zhang, G. Wu, J. M. F. Moura, J. P. Costeira, and G. J. Gordon, "Adversarial multiple source domain adaptation," in NeurIPS, 2018, pp. 8568–8579.
S. Zhao, G. Wang, S. Zhang, Y. Gu, Y. Li, Z. Song, P. Xu, R. Hu, H. Chai, and K. Keutzer, "Multi-source distilling domain adaptation," in AAAI Conf. Articial Intelligence, 2020, pp. 12 975–12 983.
S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in ICML, F. R. Bach and D. M. Blei, Eds., 2015, pp. 448–456.
P. Arbelaez, M. Maire, C. C. Fowlkes, and J. Malik, "Contour detection and hierarchical image segmentation," T-PAMI, vol. 33, no. 5, pp. 898– 916, 2011.
D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization,"in ICLR, 2015.
S. Roy, A. Siarohin, E. Sangineto, S. R. Buló, N. Sebe, and E. Ricci, "Unsupervised domain adaptation using feature-whitening and consen- sus loss," in CVPR, 2019, pp. 9471–9480.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in CVPR, 2016, pp. 770–778.
