Semantic reconstruction coupled reliable pseudo-label learning for unsupervised domain adaptation

Mengtao YANG , Yueying LIU , Gaohao YI , Hao ZHOU , Yazhou YANG , Tingjin LUO

Front. Comput. Sci. ›› 2026, Vol. 20 ›› Issue (12) : 2012389

PDF (6037KB)
Front. Comput. Sci. ›› 2026, Vol. 20 ›› Issue (12) :2012389 DOI: 10.1007/s11704-026-60257-x
Artificial Intelligence
RESEARCH ARTICLE
Semantic reconstruction coupled reliable pseudo-label learning for unsupervised domain adaptation
Author information +
History +
PDF (6037KB)

Abstract

Unsupervised domain adaptation aims to train a high-performing classifier for the unlabeled target domain by exploiting fully labeled source data, despite the distribution discrepancy between domains. Existing methods typically employ pseudo-labeling to capture target semantic information, yet overlook how unreliable labels constrain performance. Besides, traditional approaches using all source samples for target reconstruction tend to blur category boundaries, degrading its learning discriminability. To address these challenges, we propose the Semantic Reconstruction coupled Reliable Pseudo-label Learning method named as SRRPL in this paper. Specifically, a “two-step pruning” pseudo-label strategy is adopted to enhance reliability through nearest-neighbor screening and probability pruning, by enabling finer-grained characterization of target samples. Moreover, SRRPL integrates a class-level semantic reconstruction matrix that employs intra-class source samples as bases to reconstruct data from both source and target domains, thereby enhancing class discriminability. Besides, an efficient alternating iterative optimization algorithm is designed to solve our formulated non-convex objective function. Finally, extensive experimental results on multiple public datasets demonstrate our method outperforms other state-of-the-art approaches.

Graphical abstract

Keywords

semantic reconstruction / pseudo-label learning / subspace learning / unsupervised domain adaptation

Cite this article

Download citation ▾
Mengtao YANG, Yueying LIU, Gaohao YI, Hao ZHOU, Yazhou YANG, Tingjin LUO. Semantic reconstruction coupled reliable pseudo-label learning for unsupervised domain adaptation. Front. Comput. Sci., 2026, 20 (12) : 2012389 DOI:10.1007/s11704-026-60257-x

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Pan S J, Yang Q . A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22( 10): 1345–1359

[2]

Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd International Conference on Machine Learning. 2015, 1180−1189

[3]

Long M, Cao Y, Wang J, Jordan M. Learning transferable features with deep adaptation networks. In: Proceedings of the 32nd International Conference on Machine Learning. 2015, 97−105

[4]

He Y, Wang H, Li B, Zhao H . Gradual domain adaptation: theory and algorithms. The Journal of Machine Learning Research, 2024, 25( 1): 361

[5]

Perone C S, Ballester P, Barros R C, Cohen-Adad J . Unsupervised domain adaptation for medical imaging segmentation with self-ensembling. NeuroImage, 2019, 194: 1–11

[6]

Yang K, Chen H, Wang Y, Fan W, Zhou K, Xiong Y, Zhao Q, Wang J, Chang S, Xue L . Multi-granularity feature alignment network for unsupervised domain adaptation of medical image classification. Knowledge-Based Systems, 2025, 323: 113676

[7]

Guan H, Liu M . Domain adaptation for medical image analysis: a survey. IEEE Transactions on Biomedical Engineering, 2022, 69( 3): 1173–1185

[8]

Li Z, Wang X, Ai M . Prototype-combined two-stage unsupervised domain adaptation segmentation model for remote sensing images. Journal of Frontiers of Computer Science and Technology, 2024, 18( 8): 2091–2108

[9]

Zeng J, Gu Y, Qin C, Jia X, Deng S, Xu J, Tian H . Unsupervised domain adaptation for remote sensing semantic segmentation with the 2D discrete wavelet transform. Scientific Reports, 2024, 14( 1): 23552

[10]

Yu C, Xu M, Zhang Q, Lu X . Dual-intervention-constrained mask-adversary framework for unsupervised domain adaptation of hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 5509205

[11]

Fan R, Xie J, Liu J, Zhang Y, Hou H, Yang J . DPCA: dynamic multi-prototype cross-attention for change detection unsupervised domain adaptation of remote sensing images. Knowledge-Based Systems, 2025, 314: 113135

[12]

Zhu Y, Wang S, Li Y, Yuan Y, Qiang J . Soft prompt-tuning for unsupervised domain adaptation via self-supervision. Neurocomputing, 2025, 617: 129008

[13]

Malik B, Kashyap A R, Kan M Y, Poria S. UDAPTER−efficient domain adaptation using adapters. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023, 2249−2263

[14]

Pan S J, Tsang I W, Kwok J T, Yang Q . Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 2011, 22( 2): 199–210

[15]

Long M, Wang J, Ding G, Sun J, Yu P S. Transfer feature learning with joint distribution adaptation. In: Proceedings of 2013 IEEE International Conference on Computer Vision. 2013, 2200−2207

[16]

Wang J, Chen Y, Hao S, Feng W, Shen Z. Balanced distribution adaptation for transfer learning. In: Proceedings of 2017 IEEE International Conference on Data Mining. 2017, 1129−1134

[17]

Zhang W, Wu D. Discriminative joint probability maximum mean discrepancy (DJP-MMD) for domain adaptation. In: Proceedings of 2020 International Joint Conference on Neural Networks. 2020, 1−8

[18]

Gong B, Shi Y, Sha F, Grauman K. Geodesic flow kernel for unsupervised domain adaptation. In: Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012, 2066−2073

[19]

Fernando B, Habrard A, Sebban M, Tuytelaars T. Unsupervised visual domain adaptation using subspace alignment. In: Proceedings of 2013 IEEE International Conference on Computer Vision. 2013, 2960−2967

[20]

Sun B, Saenko K. Subspace distribution alignment for unsupervised domain adaptation. In: Proceedings of the British Machine Vision Conference 2015. 2015, 24

[21]

Xu Y, Fang X, Wu J, Li X, Zhang D . Discriminative transfer subspace learning via low-rank and sparse representation. IEEE Transactions on Image Processing, 2016, 25( 2): 850–863

[22]

Madadi Y, Seydi V, Hosseini R . Multi-source domain adaptation-based low-rank representation and correlation alignment. International Journal of Computers and Applications, 2022, 44( 7): 670–677

[23]

Yang L, Zhou Q, Lu B . Marginal subspace learning with group low-rank for unsupervised domain adaptation. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35( 7): 9122–9135

[24]

Yang L, Lu B, Zhou Q, Su P . Unsupervised domain adaptation via re-weighted transfer subspace learning with inter-class sparsity. Knowledge-Based Systems, 2023, 263: 110277

[25]

Liu Y, Luo T . Nonconvex and discriminative transfer subspace learning for unsupervised domain adaptation. Frontiers of Computer Science, 2025, 19( 2): 192307

[26]

Wang J, Zhang X L . Improving pseudo labels with intra-class similarity for unsupervised domain adaptation. Pattern Recognition, 2023, 138: 109379

[27]

Han N, Wu J, Fang X, Xie S, Zhan S, Xie K, Li X . Latent elastic-net transfer learning. IEEE Transactions on Image Processing, 2020, 29: 2820–2833

[28]

Li J, Jing M, Lu K, Zhu L, Shen H T . Locality preserving joint transfer for domain adaptation. IEEE Transactions on Image Processing, 2019, 28( 12): 6103–6115

[29]

Wang Y, Nie L, Li Y, Chen S . Soft large margin clustering for unsupervised domain adaptation. Knowledge-Based Systems, 2020, 192: 105344

[30]

Liang J, Hu D, Feng J. Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 6028−6039

[31]

Chen D, Wang D, Darrell T, Ebrahimi S. Contrastive test-time adaptation. In: Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022, 295−305

[32]

Feng Y, Zhu H, Peng D, Peng X, Hu P. ROAD: robust unsupervised domain adaptation with noisy labels. In: Proceedings of the 31st ACM International Conference on Multimedia. 2023, 7264−7273

[33]

Chen Z, Wu X J, Kittler J . Low-rank discriminative least squares regression for image classification. Signal Processing, 2020, 173: 107485

[34]

Han N, Wu J, Fang X, Wong W K, Xu Y, Yang J, Li X . Double relaxed regression for image classification. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30( 2): 307–319

[35]

Fang X, Xu Y, Li X, Lai Z, Wong W K, Fang B . Regularized label relaxation linear regression. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29( 4): 1006–1018

[36]

Chen Z, Wu X J, Kittler J . Relaxed block-diagonal dictionary pair learning with locality constraint for image recognition. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33( 8): 3645–3659

[37]

Lee D, Hwang K, Kwak N. Unlocking the potential of unlabeled data in semi-supervised domain generalization. In: Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2025, 30599−30608

[38]

Combettes P L, Wajs V R . Signal recovery by proximal forward-backward splitting. Multiscale Modeling & Simulation, 2005, 4( 4): 1168–1200

[39]

Sim T, Baker S, Bsat M. The CMU pose, illumination, and expression (PIE) database. In: Proceedings of the 5th IEEE International Conference on Automatic Face Gesture Recognition. 2002, 53−58

[40]

Lan M, Meng M, Yu J, Wu J . Learning to discover knowledge: a weakly-supervised partial domain adaptation approach. IEEE Transactions on Image Processing, 2024, 33: 4090–4103

[41]

Saenko K, Kulis B, Fritz M, Darrell T. Adapting visual category models to new domains. In: Proceedings of the 11th European Conference on Computer Vision. 2010, 213−226

[42]

Fei-Fei L, Fergus R, Perona P. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: Proceedings of 2004 Conference on Computer Vision and Pattern Recognition Workshop. 2004, 178

[43]

Venkateswara H, Eusebio J, Chakraborty S, Panchanathan S. Deep hashing network for unsupervised domain adaptation. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017, 5385−5394

[44]

Li W, Chen S . Unsupervised domain adaptation with progressive adaptation of subspaces. Pattern Recognition, 2022, 132: 108918

[45]

Yang L, Zhou Q . Transfer subspace learning joint low-rank representation and feature selection. Multimedia Tools and Applications, 2022, 81( 27): 38353–38373

[46]

Zheng Z, Teng S, Wu N, Teng L, Zhang W, Fei L . Selected confidence sample labeling for domain adaptation. Neurocomputing, 2023, 555: 126624

[47]

Hu L, Tan C, Tian Y . Adaptive dual-graph learning joint feature selection for EEG emotion recognition. Journal of King Saud University Computer and Information Sciences, 2025, 37( 4): 69

[48]

van der Maaten L, Hinton G . Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, 9( 28): 2579–2605

Rights & permissions

Higher Education Press

PDF (6037KB)

Supplementary files

Highlights

278

Accesses

0

Citation

Detail

Sections
Recommended

/

〈 〉