CLC number: TP181
On-line Access: 2022-12-14
Received: 2022-06-29
Revision Accepted: 2022-12-17
Crosschecked: 2022-09-22
Cited: 0
Clicked: 1968
Citations: Bibtex RefMan EndNote GB/T7714
Yikang WEI, Yahong HAN. Dual collaboration for decentralized multi-source domain adaptation[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23(12): 1780-1794.
@article{title="Dual collaboration for decentralized multi-source domain adaptation",
author="Yikang WEI, Yahong HAN",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="23",
number="12",
pages="1780-1794",
year="2022",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2200284"
}
%0 Journal Article
%T Dual collaboration for decentralized multi-source domain adaptation
%A Yikang WEI
%A Yahong HAN
%J Frontiers of Information Technology & Electronic Engineering
%V 23
%N 12
%P 1780-1794
%@ 2095-9184
%D 2022
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2200284
TY - JOUR
T1 - Dual collaboration for decentralized multi-source domain adaptation
A1 - Yikang WEI
A1 - Yahong HAN
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 23
IS - 12
SP - 1780
EP - 1794
%@ 2095-9184
Y1 - 2022
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2200284
Abstract: The goal of decentralized multi-source domain adaptation is to conduct unsupervised multi-source domain adaptation in a data decentralization scenario. The challenge of data decentralization is that the source domains and target domain lack cross-domain collaboration during training. On the unlabeled target domain, the target model needs to transfer supervision knowledge with the collaboration of source models, while the domain gap will lead to limited adaptation performance from source models. On the labeled source domain, the source model tends to overfit its domain data in the data decentralization scenario, which leads to the negative transfer problem. For these challenges, we propose dual collaboration for decentralized multi-source domain adaptation by training and aggregating the local source models and local target model in collaboration with each other. On the target domain, we train the local target model by distilling supervision knowledge and fully using the unlabeled target domain data to alleviate the domain shift problem with the collaboration of local source models. On the source domain, we regularize the local source models in collaboration with the local target model to overcome the negative transfer problem. This forms a dual collaboration between the decentralized source domains and target domain, which improves the domain adaptation performance under the data decentralization scenario. Extensive experiments indicate that our method outperforms the state-of-the-art methods by a large margin on standard multi-source domain adaptation datasets.
[1]Ahmed SM, Raychaudhuri DS, Paul S, et al., 2021. Unsupervised multi-source domain adaptation without access to source data. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.10103-10112.
[2]Cubuk ED, Zoph B, Shlens J, et al., 2020. Randaugment: practical automated data augmentation with a reduced search space. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops, p.702-703.
[3]Feng HZ, You ZY, Chen MH, et al., 2021. KD3A: unsupervised multi-source decentralized domain adaptation via knowledge distillation. Pro 38th Int Conf on Machine Learning, p.3274-3283.
[4]Ganin Y, Lempitsky V, 2015. Unsupervised domain adaptation by backpropagation. Pro 32nd Int Conf on Machine Learning, p.1180-1189.
[5]Gao Z, Guo LM, Ren TW, et al., 2022. Pairwise two-stream ConvNets for cross-domain action recognition with small data. IEEE Trans Neur Netw Learn Syst, 33(3):1147-1161.
[6]Han YH, Wu AM, Zhu LC, et al., 2021. Visual commonsense reasoning with directional visual connections. Front Inform Technol Electron Eng, 22(5):625-637.
[7]Kundu JN, Venkat N, Rahul MV, et al., 2020. Universal source-free domain adaptation. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.4544-4553.
[8]Kundu JN, Kulkarni A, Singh A, et al., 2021. Generalize then adapt: source-free domain adaptive semantic segmentation. Proc IEEE/CVF Int Conf on Computer Vision, p.7046-7056.
[9]Li R, Jiao QF, Cao WM, et al., 2020. Model adaptation: unsupervised domain adaptation without source data. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.9641-9650.
[10]Li RH, Jia X, He JZ, et al., 2021. T-SVDNet: exploring high-order prototypical correlations for multi-source domain adaptation. Proc IEEE/CVF Int Conf on Computer Vision, p.9991-10000.
[11]Li S, Song SJ, Wu C, 2018. Layer-wise domain correction for unsupervised domain adaptation. Front Inform Technol Electron Eng, 19(1):91-103.
[12]Liang J, Hu DP, Feng JS, 2020. Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. Proc 37th Int Conf on Machine Learning, p.6028-6039.
[13]Liu YA, Zhang W, Wang J, 2021. Source-free domain adaptation for semantic segmentation. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.1215-1224.
[14]Long MS, Cao Y, Wang JM, et al., 2015. Learning transferable features with deep adaptation networks. Proc 32nd Int Conf on Machine Learning, p.97-105.
[15]McMahan B, Moore E, Ramage D, et al., 2017. Communication-efficient learning of deep networks from decentralized data. Proc 20th Int Conf on Artificial Intelligence and Statistics, p.1273-1282.
[16]Miyato T, Maeda Si, Koyama M, et al., 2018. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans Patt Anal Mach Intell, 41(8):1979-1993.
[17]Nguyen VA, Nguyen T, Le T, et al., 2021. STEM: an approach to multi-source domain adaptation with guarantees. Proc IEEE/CVF Int Conf on Computer Vision, p.9352-9363.
[18]Peng XC, Bai QX, Xia XD, et al., 2019. Moment matching for multi-source domain adaptation. Proc IEEE/CVF Int Conf on Computer Vision, p.1406-1415.
[19]Peng XC, Huang ZJ, Zhu YZ, et al., 2020. Federated adversarial domain adaptation. Proc 8th Int Conf on Learning Representations, p.1-19.
[20]Pu SL, Zhao W, Chen WJ, et al., 2021. Unsupervised object detection with scene-adaptive concept learning. Front Inform Technol Electron Eng, 22(5):638-651.
[21]Qiu Z, Zhang YF, Lin HB, et al., 2021. Source-free domain adaptation via avatar prototype generation and adaptation. Proc 30th Int Joint Conf on Artificial Intelligence, p.2921-2927.
[22]Saito K, Kim D, Sclaroff S, et al., 2019. Semi-supervised domain adaptation via minimax entropy. Proc IEEE/CVF Int Conf on Computer Vision, p.8050-8058.
[23]van der Maaten L, Hinton G, 2008. Visualizing data using t-SNE. J Mach Learn Res, 9(86):2579-2605.
[24]Venkat N, Kundu JN, Singh DK, et al., 2020. Your classifier can secretly suffice multi-source domain adaptation. Proc 34th Int Conf on Neural Information Processing Systems, 33:4647-4659.
[25]Wang B, Li G, Wu C, et al., 2022. A framework for self-supervised federated domain adaptation. EURASIP J Wirel Commun Network, 2022(1):37.
[26]Wang H, Xu MH, Ni BB, et al., 2020. Learning to combine: knowledge aggregation for multi-source domain adaptation. Proc 16th European Conf on Computer Vision, p.727-744.
[27]Wu GL, Gong SG, 2021. Collaborative optimization and aggregation for decentralized domain generalization and adaptation. Proc IEEE/CVF Int Conf on Computer Vision, p.6484-6493.
[28]Xia HF, Zhao HD, Ding ZM, 2021. Adaptive adversarial network for source-free domain adaptation. Proc IEEE/CVF Int Conf on Computer Vision, p.9010-9019.
[29]Xu RJ, Chen ZL, Zuo WM, et al., 2018. Deep cocktail network: multi-source unsupervised domain adaptation with category shift. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.3964-3973.
[30]Yang LY, Balaji Y, Lim SN, et al., 2020. Curriculum manager for source selection in multi-source domain adaptation. Proc 16th European Conf on Computer Vision, p.608-624.
[31]Yang Q, Liu Y, Cheng Y, et al., 2020. Federated Learning. Springer, Cham, Germany.
[32]Yang Y, Zhuang YT, Pan YH, 2021. Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies. Front Inform Technol Electron Eng, 22(12):1551-1558.
[33]Zhao H, Zhang SH, Wu GH, et al., 2018. Adversarial multiple source domain adaptation. Proc 32nd Int Conf on Neural Information Processing Systems, p.8568-8579.
[34]Zhao SC, Li B, Yue XY, et al., 2019. Multi-source domain adaptation for semantic segmentation. Proc 33rd Int Conf on Neural Information Processing Systems, p.655.
[35]Zhao SC, Wang GZ, Zhang SH, et al., 2020. Multi-source distilling domain adaptation. Proc AAAI on Conf Artificial Intelligence, 34(7):12975-12983.
[36]Zhao SC, Li B, Xu PF, et al., 2021. Madan: multi-source adversarial domain aggregation network for domain adaptation. Int J Comput Vis, 129(8):2399-2424.
[37]Zhao YB, Zhang H, Gao Z, et al., 2022. A temporal-aware relation and attention network for temporal action localization. IEEE Trans Image Process, 31:4746-4760.
[38]Zhou KY, Yang YX, Qiao Y, et al., 2021. Domain adaptive ensemble learning. IEEE Trans Image Process, 30:8008-8018.
[39]Zuo YK, Yao HT, Xu CS, 2021. Attention-based multi-source domain adaptation. IEEE Trans Image Process, 30:3793-3803.
Open peer comments: Debate/Discuss/Question/Opinion
<1>