Abstract
We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data, but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm.
J. N. Kundu and R. M. Venkatesh are Equal contribution.
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
Similar content being viewed by others
References
Baktashmotlagh, M., Faraki, M., Drummond, T., Salzmann, M.: Learning factorized representations for open-set domain adaptation. In: ICLR (2019)
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1–2), 151–175 (2010)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NeurIPS (2007)
Castro, F.M., Marin-Jimenez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: ECCV (2018)
Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: CVPR (2019)
Chapelle, O., Zien, A.: Semi-supervised classification by low density separation. In: AISTATS (2005)
Dhar, P., Singh, R.V., Peng, K.C., Wu, Z., Chellappa, R.: Learning without memorizing. In: CVPR (2019)
Dong, N., Xing, E.P.: Domain adaption in one-shot learning. In: ECML-PKDD (2018)
Fort, S.: Gaussian prototypical networks for few-shot learning on omniglot (2017). arXiv preprint arXiv:1708.02735
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. JMLR 17(1), 2030–2096 (2016)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)
Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks (2013). arXiv preprint arXiv:1312.6211
Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: NeurIPS (2005)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: ICCV (2015)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR (2017)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: ECCV (2012)
Kingma, D.P., Ba, J.L.: Adam: A method for stochastic optimization. In: ICLR (2014)
Kundu, J.N., Gor, M., Agrawal, D., Babu, R.V.: GAN-Tree: An incrementally learned hierarchical generative framework for multi-modal data distributions. In: ICCV (2019)
Kundu, J.N., Lakkakula, N., Babu, R.V.: UM-Adapt: Unsupervised multi-task adaptation using adversarial cross-task distillation. In: ICCV (2019)
Kundu, J.N., Uppala, P.K., Pahuja, A., Babu, R.V.: Adadepth: Unsupervised content congruent adaptation for depth estimation. In: CVPR (2018)
Kundu, J.N., Venkat, N., Rahul, M.V., Venkatesh Babu, R.: Universal source-free domain adaptation. In: CVPR (2020)
Kundu, J.N., Venkat, N., Revanur, A., Rahul, M.V., Venkatesh Babu, R.: Towards inheritable models for open-set domain adaptation. In: CVPR (2020)
Kuroki, S., Charoenphakdee, N., Bao, H., Honda, J., Sato, I., Sugiyama, M.: Unsupervised domain adaptation based on source-guided discrepancy. In: AAAI (2019)
Lee, D.H.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning at ICML (2013)
Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: ICLR (2018)
Li, Z., Hoiem, D.: Learning without forgetting. TPAMI 40(12), 2935–2947 (2017)
Liu, H., Cao, Z., Long, M., Wang, J., Yang, Q.: Separate to adapt: Open set domain adaptation via progressive separation. In: CVPR (2019)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: NeurIPS (2016)
Lopes, R.G., Fenu, S., Starner, T.: Data-free knowledge distillation for deep neural networks. In: LLD Workshop at NeurIPS (2017)
Luo, Z., Zou, Y., Hoffman, J., Fei-Fei, L.F.: Label efficient learning of transferable representations across domains and tasks. In: NeurIPS (2017)
Nayak, G.K., Mopuri, K.R., Shaj, V., Radhakrishnan, V.B., Chakraborty, A.: Zero-shot knowledge distillation in deep networks. In: ICML (2019)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345–1359 (2009)
Panareda Busto, P., Gall, J.: Open set domain adaptation. In: ICCV (2017)
Pei, Z., Cao, Z., Long, M., Wang, J.: Multi-adversarial domain adaptation. In: AAAI (2018)
Peng, H., Li, J., Song, Y., Liu, Y.: Incrementally learning the hierarchical softmax function for neural language models. In: AAAI (2017)
Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: Visda: The visual domain adaptation challenge (2017). arXiv preprint arXiv:1710.06924
Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., Hinton, G.: Regularizing neural networks by penalizing confident output distributions. In: ICLR (2017)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: Incremental classifier and representation learning. In: CVPR (2017)
Ruping, S.: Incremental learning with support vector machines. In: ICDM (2001)
Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: ECCV (2010)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR (2018)
Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: ECCV (2018)
Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: Aligning domains using generative adversarial networks. In: CVPR (2018)
Shu, Y., Cao, Z., Long, M., Wang, J.: Transferable curriculum for weakly-supervised domain adaptation. In: AAAI (2019)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS (2017)
Sun, B., Saenko, K.: Deep coral: Correlation alignment for deep domain adaptation. In: ECCV Workshops (2016)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: Maximizing for domain invariance (2014). arXiv preprint arXiv:1412.3474
Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., Fu, Y.: Large scale incremental learning. In: CVPR (2019)
You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: CVPR (2019)
Zheng, Z., Hong, P.: Robust detection of adversarial attacks by modeling the intrinsic properties of deep neural networks. In: NeurIPS (2018)
Acknowledgement
This work is supported by a Wipro PhD Fellowship and a grant from Uchhatar Avishkar Yojana (UAY, IISC_010), MHRD, Govt. of India.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kundu, J.N., Venkatesh, R.M., Venkat, N., Revanur, A., Babu, R.V. (2020). Class-Incremental Domain Adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12358. Springer, Cham. https://doi.org/10.1007/978-3-030-58601-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-58601-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58600-3
Online ISBN: 978-3-030-58601-0
eBook Packages: Computer ScienceComputer Science (R0)