Abstract
The unsupervised domain adaptive classification task can learn domain-invariant features between the unlabeled target domain and the labeled source domain, thereby improving the classification performance in target domain. However, privacy protection and memory constrains often make it difficult to obtain labeled source domain samples, which become bottlenecks for the traditional domain adaptation. To this end, we propose a novel source free domain adaptive classification model. This model helps us to obtain a classifier with better effect in the target domain only by using the classifier trained in source domain and the target domain data without any source domain data. Firstly we propose a novel conditional information generative adversarial module based on combined discriminators. By confronting between combined discriminators and the generator, the middle domain with pseudo-labels is generated to solve the problem of missing source domain. Then when training the new classifier in domain adaptation module, we add a distillation loss mechanism to deal with the lack of source domain data supervision, thereby minimizing the difference between the old classifier response and the new classifier response to ensure that the network output retains the source domain information. Three groups of 10 datasets are used to verify this models. The results show that our methods can effectively solve the problem of source free domain adaptive classification and improve the classification accuracy in each domain.
Similar content being viewed by others
References
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Simonyan K, Zisserman A (2014)
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Gholenji E, Tahmoresnezhad J (2020) Joint discriminative subspace and distribution adaptation for unsupervised domain adaptation. Appl Intell 50(7):2050–2066
Yang G, Ding M, Zhang Y (2021) Bi-directional class-wise adversaries for unsupervised domain adaptation. Appl Intell 52:3623–3639
Long M, Cao Y, Wang J, Jordan M (2015) Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, PMLR, pp 97–105
Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014)
Zellinger W, Grubinger T, Lughofer E, Natschläger T, Saminger-Platz S (2017)
Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, PMLR, pp 1180–1189
Pei Z, Cao Z, Long M, Wang J (2018) Multi-adversarial domain adaptation. In: Thirty-second AAAI conference on artificial intelligence
Saito K, Watanabe K, Ushiku Y, Harada T (2018) Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3723–3732
Wang H, Shen T, Zhang W, Duan L-Y, Mei T (2020) Classes matter: A fine-grained adversarial approach to cross-domain semantic segmentation. In: European conference on computer vision, Springer, pp 642–659
Wang S, Zhang L (2020) Self-adaptive re-weighted adversarial domain adaptation. arXiv:2006.00223
Chen C, Chen Z, Jiang B, Jin X (2019) Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 33. pp 3296–3303
Sun B, Feng J, Saenko K (2016) Return of frustratingly easy domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 30.
Sun B, Saenko K (2016) Deep coral: Correlation alignment for deep domain adaptation. In: European conference on computer vision, Springer, pp 443–450
Zhuo J, Wang S, Zhang W, Huang Q (2017) Deep unsupervised convolutional domain adaptation. In: Proceedings of the 25th ACM international conference on multimedia, pp 261– 269
Pinheiro PO (2018) Unsupervised domain adaptation with similarity learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8004–8013
Lee C-Y, Batra T, Baig MH, Ulbricht D (2019) Sliced wasserstein discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10285–10295
Kurmi VK, Bajaj V, Subramanian VK, Namboodiri VP (2019) Curriculum based dropout discriminator for domain adaptation. arXiv:1907
Radford A, Metz L, Chintala S (2015)
Mirza M, Osindero S (2014)
Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232
Donahue J, Krähenbühl P, Darrell T (2016)
Donahue J, Simonyan K (2019) Large scale adversarial representation learning. Adv Neural Inf Process Syst 32:10542–10552
Li R, Jiao Q, Cao W, Wong H-S, Wu S (2020) Model adaptation: unsupervised domain adaptation without source data. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 9641–9650
Kurmi VK, Subramanian VK, Namboodiri VP (2021) Domain impression: a source data free domain adaptation method. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 615–625
Liang J, Hu D, Feng J (2020) Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: International conference on machine learning, PMLR, pp 6028–6039
Hou Y, Zheng L (2021) Visualizing adapted knowledge in domain transfer. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13824–13833
Lim JH, Ye JC (2017) Geometric gan. arXiv:1705.02894
Tran D, Ranganath R, Blei DM (2017) Hierarchical implicit models and likelihood-free variational inference. Adv Neural Inf Process Syst 2017:5524–5534
Brock A, Donahue J, Simonyan K (2018) Large scale gan training for high fidelity natural image synthesis. In: International conference on learning representations
Miyato T, Kataoka T, Koyama M, Yoshida Y (2018) Spectral normalization for generative adversarial networks. arXiv:1802.05957
Shmelkov K, Schmid C, Alahari K (2017) Incremental learning of object detectors without catastrophic forgetting. In: Proceedings of the IEEE international conference on computer vision, pp 3400–3409
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278–2324
Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(1):2096–2030
Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning
Hull JJ (1994) A database for handwritten text recognition research. IEEE Trans Pattern Anal Mach Intell 16(5):550–554
Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: European conference on computer vision, Springer, pp 213–226
Ghifary M, Kleijn WB, Zhang M, Balduzzi D, Li W (2016) Deep reconstruction-classification networks for unsupervised domain adaptation. In: European conference on computer vision, Springer, pp 597–613
Saito K, Ushiku Y, Harada T (2017) Asymmetric tri-training for unsupervised domain adaptation. In: International conference on machine learning, PMLR, pp 2988–2997
Cicek S, Soatto S (2019) Unsupervised domain adaptation via regularized conditional alignment. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1416–1425
Sankaranarayanan S, Balaji Y, Castillo CD, Chellappa R (2018) Generate to adapt: aligning domains using generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8503–8512
Tang H, Jia K (2020) Discriminative adversarial domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34. pp 5940–5947
Long M, Zhu H, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. Adv Neural Inf Process Syst 29:136–144
Long M, Zhu H, Wang J, Jordan MI (2017) Deep transfer learning with joint adaptation networks. In: International conference on machine learning, PMLR, pp 2208–2217
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Machine learning 79(1):151–175
Shen J, Qu Y, Zhang W, Yu Y (2018) Wasserstein distance guided representation learning for domain adaptation. In: Thirty-second AAAI conference on artificial intelligence
Acknowledgments
This work was supported by Joint Fund of Natural Science Foundation of Anhui Province in 2020 (2008085UD08), Anhui Provincial Key R&D Program (201904d08020008, 202004a05020004) and Intelligent Networking and New Energy Vehicle Special Project of Intelligent Manufacturing Institute of HFUT (IMIWL2019003, IMIDC2019002). In addition, it was also supported by the Fundamental Research Funds for the Central Universities(JZ2021HGQA0199), and the nurturing project for Science and Technology achievements aided by Intelligent Manufacturing Institute of HFUT(IMIPY2021020).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Chong Zhao, Yang Lu, Wei Xing and Xuanyuan Qiao are contributed equally to this work.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, Y., Zhao, C., Lu, Y. et al. A source free domain adaptation model based on adversarial learning for image classification. Appl Intell 53, 11389–11402 (2023). https://doi.org/10.1007/s10489-022-04026-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04026-w