Adaptação de Domínio usando Camadas de Alinhamento de Domínio com Várias Fontes
Resumo
Modelos profundos, frente a mudança de domínio que pode existir entre conjuntos de dados anotados de treinamento e conjuntos de dados não-anotados de teste, podem produzir resultados insatisfatórios. A mudança de domínio é objetivo das áreas de pesquisa denominadas adaptação de domínio não-supervisionada, quando adapta-se um domínio-fonte para um domínio-alvo; e a adaptação de domínio de várias fontes, a qual adapta múltiplos domínios-fonte para um único domínio-alvo. Este trabalho apresenta as camadas de alinhamento de domínio entre várias fontes (do inglês, Multi-Source DomaIn Aligment Layers – MS-DIAL), que reduzem a discrepância entre as distribuições dos domínios-fonte e do domínio-alvo a partir da inserção de camadas de alinhamento de domínio em diversos níveis da rede. Foram realizados experimentos em tarefas de reconhecimento de dígitos e de objetos, os quais obtiveram resultados promissores que superam métodos do estado da arte.Referências
F. M. Carlucci, L. Porzi, B. Caputo, E. Ricci, and S. R. Bul`o, "Just DIAL: domain alignment layers for unsupervised domain adaptation," in Int. Conf. Image Analysis and Processing, 2017, pp. 357–369.
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.
H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Panchanathan, "Deep hashing network for unsupervised domain adaptation," in CVPR, 2017, pp. 5385–5394.
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. Bul`o, "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.
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.
J. Wen, R. Greiner, and D. Schuurmans, "Domain aggregation networks for multi-source domain adaptation," in ICML, 2020, pp. 10 927–10 937.
Y. Li, M. Murias, G. Dawson, and D. E. Carlson, "Extracting relati- onships 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. Artificial 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.
S. Roy, A. Siarohin, E. Sangineto, S. R. Bul`o, N. Sebe, and E. Ricci, "Unsupervised domain adaptation using feature-whitening and consensus 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.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. S. Bernstein, A. C. Berg, and F.-F. Li, "Imagenet large scale visual recognition challenge," IJCV, vol. 115, no. 3, pp. 211–252, 2015.
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.
H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Panchanathan, "Deep hashing network for unsupervised domain adaptation," in CVPR, 2017, pp. 5385–5394.
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. Bul`o, "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.
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.
J. Wen, R. Greiner, and D. Schuurmans, "Domain aggregation networks for multi-source domain adaptation," in ICML, 2020, pp. 10 927–10 937.
Y. Li, M. Murias, G. Dawson, and D. E. Carlson, "Extracting relati- onships 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. Artificial 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.
S. Roy, A. Siarohin, E. Sangineto, S. R. Bul`o, N. Sebe, and E. Ricci, "Unsupervised domain adaptation using feature-whitening and consensus 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.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. S. Bernstein, A. C. Berg, and F.-F. Li, "Imagenet large scale visual recognition challenge," IJCV, vol. 115, no. 3, pp. 211–252, 2015.
Publicado
07/11/2020
Como Citar
E SILVA, Lucas Fernando Alvarenga; ALMEIDA, Jurandy.
Adaptação de Domínio usando Camadas de Alinhamento de Domínio com Várias Fontes. In: WORKSHOP DE TRABALHOS DA GRADUAÇÃO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 33. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 199-202.
DOI: https://doi.org/10.5753/sibgrapi.est.2020.13011.
