Abstract
Traditional unsupervised domain adaptation (UDA) aims to transfer the learned knowledge from a fully labeled source domain to another unlabeled target domain on the same label set. The strong assumptions of full annotations on the source domain and a closed label set of the two domains might not hold in real-world applications. In this paper, we investigate a practical but challenging domain adaptation scenario, termed few-shot universal domain adaptation (FUniDA), where only a few labeled data are available in the source domain and the label sets of the source and target domains are different. Existing few-shot UDA (FUDA) methods and universal domain adaptation (UniDA) methods cannot address this novel domain adaptation setting well. The FUDA methods would misalign the unknown samples of the target domain and the private samples of the source domain, and the UniDA methods cannot perform well with only a small number of labeled source samples. To address these challenges, we propose a novel domain consensual contrastive learning (DCCL) framework for FUniDA. Specifically, DCCL comprises two major components: 1) in-domain consensual contrastive learning aims to learn discriminative features from few labeled source data, and 2) cluster matching and cross-domain consensual contrastive learning aim to align the features of common samples in the source and target domains while keeping the private samples as private. We conduct extensive experiments on five standard benchmark datasets, including Office-31, Office-Home, VisDA-17, DomainNet, and ImageCLEF-DA. The results demonstrate that the proposed DCCL achieves state-of-the-art performance with remarkable gains.
Similar content being viewed by others
Notes
Following [30], we use common samples, private samples, known samples, and unknown samples to refer to the samples that belong to the common classes, private classes, known classes, and unknown classes of the source and target domains.
References
Alipour N, Tahmoresnezhad J (2022) Heterogeneous domain adaptation with statistical distribution alignment and progressive pseudo label selection. Appl Intell 52:1–18
Chen J, Wu X, Duan L, Gao S (2020) Domain adversarial reinforcement learning for partial domain adaptation. IEEE Trans Neural Netw Learn Syst 33(2):539–553
Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning. pp 1597–1607
Chen Y, Song S, Li S, Wu C (2019) A graph embedding framework for maximum mean discrepancy-based domain adaptation algorithms. IEEE Trans Image Process 29:199–213
Cheng Z, Chen C, Chen Z, Fang K, Jin X (2021) Robust and high-order correlation alignment for unsupervised domain adaptation. Neural Comput Appl 33:6891–6903
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition. pp 248–255
Ebrahimi M, Chai Y, Zhang H H, Chen H (2022) Heterogeneous domain adaptation with adversarial neural representation learning: Experiments on e-commerce and cybersecurity. IEEE Trans Pattern Anal Mach Intell 45:1862–1875
Fang Z, Lu J, Liu F, Xuan J, Zhang G (2021) Open set domain adaptation: Theoretical bound and algorithm. IEEE Trans Neural Netw Learn Syst 32(10):4309–4322
Feng H, Chen M, Hu J, Shen D, Liu H, Cai D (2021) Complementary pseudo labels for unsupervised domain adaptation on person re-identification. IEEE Trans Image Process 30:2898–2907
Fu B, Cao Z, Long M, Wang J (2020) Learning to detect open classes for universal domain adaptation. In: European Conference on Computer Vision. pp 567–583
He K, Chen X, Xie S, Li Y, Dollár P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp 16000–16009
He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp 9729–9738
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition. pp 770–778
He Q-Q, Siu SWI, Si Y-W (2022) Attentive recurrent adversarial domain adaptation with top-k pseudo-labeling for time series classification. Appl Intell 53:1–20
Huang J, Zhang P, Zhou Z, Fan K (2021) Domain compensatory adversarial networks for partial domain adaptation. Multimed Tools Appl 80:11255–11272
Kouw WM, Loog M (2021) A review of domain adaptation without target labels. IEEE Trans Pattern Anal Mach Intell 43(3):766–785
Kutbi M, Peng K-C, Wu Z (2021) Zero-shot deep domain adaptation with common representation learning. IEEE Trans Pattern Anal Mach Intell 44(7):3909–3924
Li G, Kang G, Zhu Y, Wei Y, Yang Y (2021) Domain consensus clustering for universal domain adaptation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp 9757–9766
Li H, Wan R, Wang S, Kot AC (2021) Unsupervised domain adaptation in the wild via disentangling representation learning. Int J Comput Vis 129:267–283
Li S, Liu CH, Lin Q, Wen Q, Su L, Huang G, Ding Z (2020) Deep residual correction network for partial domain adaptation. IEEE Trans Pattern Anal Mach Intell 43(7):2329–2344
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems. pp 8024–8035
Peng X, Bai Q, Xia X, Huang Z, Saenko K, Wang B (2019) Moment matching for multi-source domain adaptation. In: IEEE International Conference on Computer Vision. pp 1406–1415
Peng X, Usman B, Kaushik N, Wang D, Hoffman J, Saenko K (2018) Visda: A synthetic-to-real benchmark for visual domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp 2021–2026
Qin Z, Yang L, Gao F, Hu Q, Shen C (2022) Uncertainty-aware aggregation for federated open set domain adaptation. IEEE Trans Neural Netw Learn Syst
Rahman MM, Fookes C, Baktashmotlagh M, Sridharan S (2020) Correlation-aware adversarial domain adaptation and generalization. Pattern Recognit 100:107124
Ren C-X, Ge P, Yang P, Yan S (2020) Learning target-domain-specific classifier for partial domain adaptation. IEEE Trans Neural Netw Learn Syst 32(5):1989–2001
Ren Y, Cong Y, Dong J, Sun G (2022) Uni3da: Universal 3d domain adaptation for object recognition. IEEE Trans Circ Syst Video Technol 33:379–392
Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: European Conference on Computer Vision. pp 213–226
Saito K, Kim D, Sclaroff S, Saenko K (2020) Universal domain adaptation through self supervision. In: Advances in Neural Information Processing Systems. pp 16282–16292
Saito K, Saenko K (2021) Ovanet: One-vs-all network for universal domain adaptation. In: IEEE International Conference on Computer Vision. pp 9000–9009
Shermin T, Lu G, Teng SW, Murshed M, Sohel F (2020) Adversarial network with multiple classifiers for open set domain adaptation. IEEE Trans Multimedia 23:2732–2744
Tian Y, Zhu S (2021) Partial domain adaptation on semantic segmentation. IEEE Trans Circ Syst Video Technol 32(6):3798–3809
Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11):2579–2605
Venkateswara H, Eusebio J, Chakraborty S, Panchanathan S (2017) Deep hashing network for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition. pp 5018–5027
Wang W, Li H, Ding Z, Nie F, Chen J, Dong X, Wang Z (2021) Rethinking maximum mean discrepancy for visual domain adaptation. IEEE Trans Neural Netw Learn Syst 34:264–277
Wang W, Shen Z, Li D, Zhong P, Chen Y (2022) Probability-based graph embedding cross-domain and class discriminative feature learning for domain adaptation. IEEE Trans Image Process 32:72–87
Wynne G, Duncan AB (2022) A kernel two-sample test for functional data. J Mach Learn Res 23(73):1–51
Xu Q, Shi Y, Yuan X, Zhu XX (2023) Universal domain adaptation for remote sensing image scene classification. IEEE Trans Geosci Remote Sens 61:1–15
Xu Y, Cao H, Mao K, Chen Z, Xie L, Yang J (2022) Aligning correlation information for domain adaptation in action recognition. IEEE Trans Neural Netw Learn Syst
Yan H, Li Z, Wang Q, Li P, Xu Y, Zuo W (2019) Weighted and class-specific maximum mean discrepancy for unsupervised domain adaptation. IEEE Trans Multimedia 22(9):2420–2433
Ye Y, Fu S, Chen J (2023) Learning cross-domain representations by vision transformer for unsupervised domain adaptation. Neural Comput Appl 35:1–14
Yin Y, Yang Z, Hu H, Wu X (2022) Universal multi-source domain adaptation for image classification. Pattern Recogn 121:108238
You K, Long M, Cao Z, Wang J, Jordan MI (2019) Universal domain adaptation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp 2720–2729
Yue X, Zheng Z, Zhang S, Gao Y, Darrell T, Keutzer K, Vincentelli A S (2021) Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp 13834–13844
Zhang S, Chen Z, Wang D, Wang ZJ (2022) Cross-domain few-shot contrastive learning for hyperspectral images classification. IEEE Geosci Remote Sens Lett 19:1–5
Zhang W, Li X, Ma H, Luo Z, Li X (2021) Open-set domain adaptation in machinery fault diagnostics using instance-level weighted adversarial learning. IEEE Trans Ind Inform 17(11):7445–7455
Zhao S, Li B, Xu P, Yue X, Ding G, Keutzer K (2021) Madan: multi-source adversarial domain aggregation network for domain adaptation. Int J Comput Vis 129(8):2399–2424
Zhao S, Yue X, Zhang S, Li B, Zhao H, Wu B, Krishna R, Gonzalez JE, Sangiovanni-Vincentelli AL, Seshia SA et al (2022) A review of single-source deep unsupervised visual domain adaptation. IEEE Trans Neural Netw Learn Syst 33(2):473–493
Zhao X, Wang S, Sun Q (2023) Open-set domain adaptation by deconfounding domain gaps. Appl Intell 53(7):7862–7875
Zhou J, Jing B, Wang Z, Xin H, Tong H (2021) Soda: Detecting covid-19 in chest x-rays with semi-supervised open set domain adaptation. IEEE/ACM Trans Comput Biol Bioinforma 19(5):2605–2612
Zhu Y, Sun X, Diao W, Li H, Fu K (2022) Rfa-net: Reconstructed feature alignment network for domain adaptation object detection in remote sensing imagery. IEEE J Sel Top Appl Earth Obs Remote Sens 15:5689–5703
Zhu Y, Wu X, Qiang J, Yuan Y, Li Y (2023) Representation learning via an integrated autoencoder for unsupervised domain adaptation. Front Comput Sci 17(5):175334
Caputo B, Müller H, Martinez-Gomez J, Villegas M, Acar B, Patricia N, Marvasti N, Üsküdarlı S, Paredes R, Cazorla M, et al (2014) Imageclef 2014: Overview and analysis of the results. In: Information Access Evaluation. Multilinguality, Multimodality, and Interaction. pp 192–211
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: IEEE International Conference on Computer Vision. pp 10012–10022
Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S (2022) A convnet for the 2020s. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp 11976–11986
Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. pp. 6105–6114
Xie S, Girshick R, Dollár P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1492–1500
Funding
This paper is supported partly by National Natural Science Foundation of China (62071066) andFundamental Research Funds for the Central Universities(2242022k60006).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no competing interests that are relevant to the content of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) 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
Liao, H., Wang, Q., Zhao, S. et al. Domain consensual contrastive learning for few-shot universal domain adaptation. Appl Intell 53, 27191–27206 (2023). https://doi.org/10.1007/s10489-023-04890-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04890-0