Abstract
With Domain Adaptation we aim to leverage a given source dataset to model a classifier on the target domain. In an unsupervised setting, the goal is to derive class-based features and adapt it to a different domain. Minimizing discrepancy between these domains is one of the most promising directions to training a common classifier. There have been several algorithmic and deep modelling approaches to this problem, all trying to combat the inherent problem of finding an ideal objective function. Recent algorithmic approaches focus on extracting domain-invariant features by minimizing the distributional and geometrical divergence between domains simultaneously. In this work, we present the results of adding generated synthetic images to some renowned shallow algorithmic approaches. Using Generative Adversarial Networks (GANs), we generate images using categorical information from source domain, thus, adding variance and variety to the source data. We present the impact of synthetic data on notable unsupervised domain adaptation algorithms and show an improvement in about 62% of the 80 task results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sim, T., Baker, S., Bsat, M.: The CMU Pose, Illumination, and Expression Database. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1615–1618 (2003)
Zhang, Y.: A Survey of Unsupervised Domain Adaptation for Visual Recognition. arXiv preprint arXiv:2112.06745 (2021)
Wilson, G., Cook, D.J.: A survey of unsupervised deep domain adaptation. ACM Trans. Intell. Syst. Technol. (TIST) 11(5), 1–46 (2020)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5018–5027 (2017)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018)
Jack, C., et al.: The Alzheimer’s Disease neuroimaging initiative (ADNI): MRI methods. J. Magn. Reson. Imaging JMRI 27, 685–691 (2008). https://doi.org/10.1002/jmri.21049
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: IEEE International Conference on Computer Vision (2015)
Gretton, A., Borgwardt, K., Rasch, M., Scholkopf, B., Smola, A.: A kernel method for the two-sample-problem. In: Scholkopf, B., Platt, J., Hoffman, T. (eds.) Advances in Neural Information Processing Systems, vol. 19. MIT Press (2006). https://proceedings.neurips.cc/paper/2006/file/e9fb2eda3d9c55a0d89c98d6c54b5b3e-Paper.pdf
Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)
Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: International Conference on Machine Learning, pp. 1989–1998. PMLR (2018)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: 2011 International Conference on Computer Vision, pp. 999–1006. IEEE (2011)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2066–2073. IEEE (2012)
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Networks 22(2), 199–210 (2010)
Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2960–2967 (2013)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with Joint Distribution Adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2200–2207 (2013)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer joint matching for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1410–1417 (2014)
Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1859–1867 (2017)
Sanodiya, R.K., Yao, L.: Linear discriminant analysis via pseudo labels: a unified framework for visual domain adaptation. IEEE Access 8, 200073–200090 (2020)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Donahue, J., Krahenbuhl, P., Darrell, T.: Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Jaiswal, A., AbdAlmageed, W., Wu, Y., Natarajan, P.: Bidirectional conditional generative adversarial networks. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 216–232. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20893-6_14
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Suryavardan, S., Pulabaigari, V., Sanodiya, R.K. (2023). Unsupervised Domain Adaptation Supplemented with Generated Images. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1791. Springer, Singapore. https://doi.org/10.1007/978-981-99-1639-9_55
Download citation
DOI: https://doi.org/10.1007/978-981-99-1639-9_55
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1638-2
Online ISBN: 978-981-99-1639-9
eBook Packages: Computer ScienceComputer Science (R0)