Robust Multi-Source Batch Normalisation for Test-Time Batch Adaptation

Xinlin Xiao , Xiangtao Zheng , Jianhua Tao , Xiaoqiang Lu

CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (5) : 1567 -1584.

PDF (1807KB)
CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (5) :1567 -1584. DOI: 10.1049/cit2.70159
ORIGINAL RESEARCH
research-article
Robust Multi-Source Batch Normalisation for Test-Time Batch Adaptation
Author information +
History +
PDF (1807KB)

Abstract

Test-Time Batch Adaptation (TTBA) aims to adapt a pre-trained source model to small, unlabelled target batches at test time. The TTBA methods focus on adapting the pre-trained model or the target data in a one-to-one alignment paradigm. However, these one-to-one alignment paradigms assume that the source domain may share the same knowledge with the target domain. It becomes ineffective when the target domain is different from the source domain. In this paper, a multi-source batch normalisation method is introduced. Specifically, spectral similarity clustering selects a small set of representative source domains, spectral entropy-guided weighting combines source statistics based on their relevance to the target domain, and batch-wise re-initialisation with unsupervised refinement stabilises updates. Extensive experiments on multiple benchmark datasets verify the effectiveness of the proposed method, achieving superior performance over state-of-the-art TTBA methods, especially in scenarios with small target batches.

Keywords

multi-source batch normalisation / source domain selection / spectral entropy weighting / test-time batch adaptation

Cite this article

Download citation ▾
Xinlin Xiao, Xiangtao Zheng, Jianhua Tao, Xiaoqiang Lu. Robust Multi-Source Batch Normalisation for Test-Time Batch Adaptation. CAAI Transactions on Intelligence Technology, 2026, 11 (5) : 1567-1584 DOI:10.1049/cit2.70159

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

J. Wang, M. M. Cheng, and J. Jiang, “ Domain Shift Preservation for Zero-Shot Domain Adaptation,” IEEE Transactions on Image Processing 30 (2021): 5505-5517, https://doi.org/10.1109/tip.2021.3084354.

[2]

Z. Wu, G. Luo, Z. Yang, Y. Guo, K. Li, and Y. Xue, “ A Comprehensive Review on Deep Learning Approaches in Wind Forecasting Applications,” CAAI Transactions on Intelligence Technology 7, no. 2 (2022): 129-143, https://doi.org/10.1049/cit2.12076.

[3]

X. Huang and S. H. Choi, “ Learning Feature Alignment and Dual Correlation for Few-Shot Image Classification,” CAAI Transactions on Intelligence Technology 9, no. 2 (2024): 303-318, https://doi.org/10.1049/cit2.12273.

[4]

W. Wang, Z. Shen, D. Li, P. Zhong, and Y. Chen, “ Probability-Based Graph Embedding Cross-Domain and Class Discriminative Feature Learning for Domain Adaptation,” IEEE Transactions on Image Processing 32 (2023): 72-87, https://doi.org/10.1109/tip.2022.3226405.

[5]

T. Shermin, G. Lu, S. W. Teng, M. Murshed, and F. Sohel, “ Adversarial Network With Multiple Classifiers for Open Set Domain Adaptation,” IEEE Transactions on Multimedia 23 (2021): 2732-2744, https://doi.org/10.1109/tmm.2020.3016126.

[6]

J. Sun, Z. Wang, W. Wang, H. Li, and F. Sun, “ Domain Adaptation With Geometrical Preservation and Distribution Alignment,” Neurocomputing 454 (2021): 152-167, https://doi.org/10.1016/j.neucom.2021.04.098.

[7]

M. M. Eltoukhy, F. S. Alsubaei, M. M. Abdel-Aziz, and K. M. Hosny, “ RDHNet: Reversible Data Hiding Method for Securing Colour Images Using AlexNet and Watershed Transform in a Fusion Domain,” CAAI Transactions on Intelligence Technology 10, no. 5 (2025): 1422-1445, https://doi.org/10.1049/cit2.70038.

[8]

D. Tuia, J. Munoz-Mari, and G. Camps-Valls, “ Kernel Manifold Alignment for Domain Adaptation,” PLoS One 11, no. 2 (2016): 0148655, https://doi.org/10.1371/journal.pone.0148655.

[9]

S. Tang, W. Su, Y. Yang, L. Chen, and M. Ye, “ Model Adaptation via Credible Local Context Representation,” CAAI Transactions on Intelligence Technology 10, no. 3 (2025): 638-651, https://doi.org/10.1049/cit2.12228.

[10]

N. Alqahtani, A. A. Khan, R. K. Mahendran, and M. Faheem, “ VSMI2-PANet: Versatile Scale-Malleable Image Integration and Patch Wise Attention Network With Transformer for Lung Tumour Segmentation Using Multi-Modal Imaging Techniques,” CAAI Transactions on Intelligence Technology 10, no. 5 (2025): 1376-1393, https://doi.org/10.1049/cit2.70039.

[11]

Z. Niu, J. Yuan, X. Ma, et al., “ Knowledge Distillation-Based Domain-Invariant Representation Learning for Domain Generalization,” IEEE Transactions on Multimedia 26 (2024): 245-255, https://doi.org/10.1109/tmm.2023.3263549.

[12]

Y. Chen, Q. Wang, J. Yang, B. Chen, H. Xiong, and S. Du, “ CSCC: Cross-Scene Crowd Counting via Learning to Diversify for Domain Generalization,” IEEE Transactions on Multimedia 27 (2025): 3320-3330, https://doi.org/10.1109/tmm.2025.3535302.

[13]

T. S. Haque, A. Chakraborty, S. P. Mondal, and S. Alam, “ Approach to Solve Multi-Criteria Group Decision-Making Problems by Exponential Operational Law in Generalised Spherical Fuzzy Environment,” CAAI Transactions on Intelligence Technology 5, no. 2 (2020): 106-114, https://doi.org/10.1049/trit.2019.0078.

[14]

A. Gasparin, S. Lukovic, and C. Alippi, “ Deep Learning for Time Series Forecasting: The Electric Load Case,” CAAI Transactions on Intelligence Technology 7, no. 1 (2022): 1-25, https://doi.org/10.1049/cit2.12060.

[15]

M. Ghifary, D. Balduzzi, W. B. Kleijn, and M. Zhang, “ Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization,” IEEE Transactions on Pattern Analysis and Machine Intelligence 39, no. 7 (2017): 1414-1430, https://doi.org/10.1109/tpami.2016.2599532.

[16]

Y. Su, X. Xu, T. Li, and K. Jia, “ Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training,” IEEE Transactions on Pattern Analysis and Machine Intelligence 46, no. 8 (2024): 5524-5540, https://doi.org/10.1109/tpami.2024.3370963.

[17]

J. Liang, D. Hu, and J. Feng, “ Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation,” in International Conference on Machine Learning (2020), 6028-6039, https://doi.org/10.48550/arXiv.2002.08546.

[18]

J. Ma, “ Improved Self-Training for Test-Time Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024), 23701-23710, https://doi.org/10.1109/CVPR52733.2024.02237.

[19]

M. Tan, G. Chen, J. Wu, et al., “ Uncertainty-Calibrated Test-Time Model Adaptation Without Forgetting,” IEEE Transactions on Pattern Analysis and Machine Intelligence 47, no. 8 (2025): 6274-6289, https://doi.org/10.1109/tpami.2025.3560696.

[20]

Y. Tang, S. Chen, Z. Kan, Y. Zhang, Q. Guo, and Z. He, “ Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptation,” IEEE Transactions on Multimedia (2024): 1-12, https://doi.org/10.1109/tmm.2024.3443633.

[21]

C. Mu, J. Peng, and Y. Tang, “Learning-Based Control for Discrete-Time Constrained Nonzero-Sum Games,” CAAI Transactions on Intelligence Technology 6, no. 2 (2021): 203-213, https://doi.org/10.1049/cit2.12015.

[22]

S. M. Ayyoubzadeh, W. Liu, I. Kezele, et al., “ Test-Time Adaptation for Optical Flow Estimation Using Motion Vectors,” IEEE Transactions on Image Processing 32 (2023): 4977-4988, https://doi.org/10.1109/tip.2023.3309108.

[23]

Z. Wen, S. Niu, G. Li, Q. Wu, M. Tan, and Q. Wu, “ Test-Time Model Adaptation for Visual Question Answering With Debiased Self-Supervisions,” IEEE Transactions on Multimedia 26 (2024): 2137-2147, https://doi.org/10.1109/tmm.2023.3292597.

[24]

Y. Yu, S. Shin, S. Back, M. Ko, S. Noh, and K. Lee, “ Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024), 22723-22732.

[25]

Z. Nado, S. Padhy, D. Sculley, A. D’Amour, B. Lakshminarayanan, and J. Snoek, “ Evaluating Prediction-Time Batch Normalization for Robustness Under Covariate Shift,” in Proceedings of ICML Workshops (2020), https://arxiv.org/abs/2006.10963.

[26]

Y. Li, N. Wang, J. Shi, X. Hou, and J. Liu, “ Adaptive Batch Normalization for Practical Domain Adaptation,” Pattern Recognition 80 (2018): 109-117, https://doi.org/10.1016/j.patcog.2018.03.005.

[27]

H. Nam and H. E. Kim, “ Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks,” in Advances in Neural Information Processing Systems (NeurIPS), ed. S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, Vol. 31 (2018), https://arxiv.org/abs/1805.07925.

[28]

N. Karani, E. Erdil, K. Chaitanya, and E. Konukoglu, “ Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation,” Medical Image Analysis 68 (2021): 101907, https://doi.org/10.1016/j.media.2020.101907.

[29]

H. Li, H. Liu, D. Hu, et al., “ Self-Supervised Test-Time Adaptation for Medical Image Segmentation,” in Machine Learning in Clinical Neuroimaging (2022), 32-41, https://doi.org/10.1007/978-3-031-17899-3_4.

[30]

M. Shu, W. Nie, D. A. Huang, et al., “ Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models,” Advances in Neural Information Processing Systems 35 (2022): 14274-14289, https://arxiv.org/abs/2209.07511.

[31]

X. Lu, T. Gong, and X. Zheng, “ Multisource Compensation Network for Remote Sensing Cross-Domain Scene Classification,” IEEE Transactions on Geoscience and Remote Sensing 58, no. 4 (2020): 2504-2515, https://doi.org/10.1109/tgrs.2019.2951779.

[32]

L. Li, J. Gou, W. Ou, W. Chen, and L. Du, “ Contrastive Learning-Based Multi-Level Knowledge Distillation,” CAAI Transactions on Intelligence Technology 10, no. 5 (2025): 1478-1488, https://doi.org/10.1049/cit2.70036.

[33]

C. Hua, X. Cao, J. Li, and S. Li, “ Fixed-Time Zeroing Neural Dynamics for Adaptive Coordination of Multi-Agent Systems,” CAAI Transactions on Intelligence Technology 11, no. 1 (2026): 267-278, https://doi.org/10.1049/cit2.70089.

[34]

D. Wang, E. Shelhamer, S. Liu, B. Olshausen, and T. Darrell, “ Tent: Fully Test-Time Adaptation by Entropy Minimization,” in International Conference on Learning Representations (2021), https://doi.org/10.48550/arXiv.2006.10726.

[35]

Q. Wang, O. Fink, L. Van Gool, and D. Dai, “ Continual Test-Time Domain Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022), 7191-7201, https://doi.org/10.1109/CVPR52688.2022.00706.

[36]

L. Yuan, B. Xie, and S. Li, “ Robust Test-Time Adaptation in Dynamic Scenarios,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023), 15922-15932, https://doi.org/10.1109/CVPR52729.2023.01528.

[37]

M. Döbler, R. A. Marsden, and B. Yang, “ Robust Mean Teacher for Continual and Gradual Test-Time Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023), 7704-7714, https://doi.org/10.1109/CVPR52729.2023.00744.

[38]

S. Niu, J. Wu, Y. Zhang, et al., “ Towards Stable Test-Time Adaptation in Dynamic Wild World,” in International Conference on Learning Representations (2023), https://doi.org/10.48550/arXiv.2302.12400.

[39]

S. Niu, J. Wu, Y. Zhang, et al., “ Efficient Test-Time Model Adaptation Without Forgetting,” in Machine Learning in Clinical Neuroimaging, Vol. 162 (2022), 16888-16905, https://doi.org/10.48550/arXiv.2204.02610.

[40]

J. Lee, D. Jung, S. Lee, et al., “ Entropy Is Not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors,” in International Conference on Learning Representations (2024), https://doi.org/10.48550/arXiv.2403.07366.

[41]

Z. Gao, X. Y. Zhang, and C. L. Liu, “ Unified Entropy Optimization for Open-Set Test-Time Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024), 23975-23984, https://doi.org/10.1109/CVPR52733.2024.02263.

[42]

C. K. Mummadi, R. Hutmacher, K. Rambach, E. Levinkov, T. Brox, and J. H. Metzen, “ Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation,” arXiv preprint arXiv: 2106.14999 (2021), https://doi.org/10.48550/arXiv.2106.14999.

[43]

X. Zhao, C. Liu, A. Sicilia, S. J. Hwang, and Y. Fu, “ Test-Time Fourier Style Calibration for Domain Generalization,” in Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (2022), 1721-1727, https://doi.org/10.24963/ijcai.2022/240.

[44]

Y. Y. Tsai, C. Mao, and J. Yang, “ Convolutional Visual Prompt for Robust Visual Perception,” in Advances in Neural Information Processing Systems, Vol. 36 (2023), https://doi.org/10.5555/3666122.3667333.

[45]

J. A. Termöhlen, M. Klingner, L. J. Brettin, N. M. Schmidt, and T. Fingscheidt, “ Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer,” in IEEE International Intelligent Transportation Systems Conference (2021), 2881-2888, https://doi.org/10.1109/ITSC48978.2021.9564566.

[46]

M. Alfarra, J. C. Pérez, A. Thabet, A. Bdi, P. H. S. Torr, and B. Ghanem, “ Combating Adversaries With Anti-Adversaries,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, no. 6 (2022), 5992-6000, https://doi.org/10.1609/aaai.v36i6.20545.

[47]

Y. Gan, X. Ma, Y. Lou, et al., “ Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, no. 6 (2023), 7595-7603, https://doi.org/10.1609/aaai.v37i6.25922.

[48]

M. Zhang, S. Levine, and C. Finn, “ MEMO: Test Time Robustness via Adaptation and Augmentation,” in Advances in Neural Information Processing Systems, Vol. 35 (2022), 38629-38642, https://doi.org/10.5555/3600270.3603069.

[49]

Y. Lu, H. Huang, X. Hu, Z. Lai, and X. Li, “ Multiple Adaptation Network for Multi-Source and Multi-Target Domain Adaptation,” IEEE Transactions on Multimedia 27 (2025): 1-15, https://doi.org/10.1109/tmm.2025.3543094.

[50]

Y. Zuo, H. Yao, and C. Xu, “ Attention-Based Multi-Source Domain Adaptation,” IEEE Transactions on Image Processing 30 (2021): 3793-3803, https://doi.org/10.1109/tip.2021.3065254.

[51]

G. Kang, L. Jiang, Y. Wei, Y. Yang, and A. Hauptmann, “ Contrastive Adaptation Network for Single- and Multi-Source Domain Adaptation,” IEEE Transactions on Pattern Analysis and Machine Intelligence 44, no. 4 (2022): 1793-1804, https://doi.org/10.1109/tpami.2020.3029948.

[52]

F. Qiao, L. Zhao, and X. Peng, “ Learning to Learn Single Domain Generalization,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020), 12553-12562, https://doi.org/10.1109/CVPR42600.2020.01257.

[53]

Y. Ganin, E. Ustinova, H. Ajakan, et al., “ Domain-Adversarial Training of Neural Networks,” Journal of Machine Learning Research 17, no. 59 (2016): 1-35, https://doi.org/10.5555/2946645.2946704.

[54]

M. Long, Z. Cao, J. Wang, and M. I. Jordan, “ Conditional Adversarial Domain Adaptation,” in Advances in Neural Information Processing Systems, Vol. 31 (2018), 1647-1657, https://doi.org/10.5555/3326943.3327094.

[55]

A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. Smola, “ A Kernel Two-Sample Test,” Journal of Machine Learning Research 13, no. 1 (2012): 723-773, https://doi.org/10.5555/2188385.2188410.

[56]

B. Sun and K. Saenko, “ Deep Coral: Correlation Alignment for Deep Domain Adaptation,” in Computer Vision - ECCV 2016 Workshops (Springer, 2016), 443-450, https://doi.org/10.1007/978-3-319-49409-8_35.

[57]

N. Courty, R. Flamary, A. Habrard, and A. Rakotomamonjy, “ Joint Distribution Optimal Transportation for Domain Adaptation,” in Advances in Neural Information Processing Systems, Vol. 30 (2017), 3733-3742, https://doi.org/10.5555/3294996.3295130.

[58]

S. Lü, M. Kang, and X. Li, “ Alleviating Imbalanced Pseudo-Label Distribution: Self-Supervised Multi-Source Domain Adaptation With Label-Specific Confidence,” in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (2024), 4669-4677, https://doi.org/10.24963/ijcai.2024/516.

[59]

Y. Balaji, S. Sankaranarayanan, and R. Chellappa, “ MetaReg: Towards Domain Generalization Using Meta-Regularization,” in Advances in Neural Information Processing Systems, Vol. 31 (2018), 998-1008, https://doi.org/10.5555/3326943.3327036.

[60]

H. Li, S. J. Pan, S. Wang, and A. C. Kot, “ Domain Generalization With Adversarial Feature Learning,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), 5400-5409, https://doi.org/10.1109/CVPR.2018.00566.

[61]

S. Gidaris, P. Singh, and N. Komodakis, “ Unsupervised Representation Learning by Predicting Image Rotations,” in International Conference on Learning Representations (2018), https://doi.org/10.48550/arXiv.1803.07728.

[62]

H. Zhang and YNDDLP, “ Mixup: Beyond Empirical Risk Minimization,” in International Conference on Learning Representations (2018), https://doi.org/10.48550/arXiv.1710.09412.

[63]

K. Zhou, Y. Yang, Y. Qiao, and T. Xiang, “ Mixstyle Neural Networks for Domain Generalization and Adaptation,” International Journal of Computer Vision 132, no. 3 (2024): 822-836, https://doi.org/10.1007/s11263-023-01913-8.

[64]

Q. Xu, R. Zhang, Y. Zhang, Y. Wang, Q. Tian, “ A Fourier-Based Framework for Domain Generalization,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021), 14378-14387, https://doi.org/10.1109/CVPR46437.2021.01415.

[65]

D. Cheng, Z. Xu, X. Jiang, N. Wang, D. Li, and X. Gao, “ Disentangled Prompt Representation for Domain Generalization,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024), 23595-23604, https://doi.org/10.1109/CVPR52733.2024.02227.

[66]

M. Aminbeidokhti, F. A. G. Peña, H. R. Medeiros, T. Dubail, E. Granger, and M. Pedersoli, “ Domain Generalization by Rejecting Extreme Augmentations,” in IEEE/CVF Winter Conference on Applications of Computer Vision (2024), 2204-2214, https://doi.org/10.1109/WACV57701.2024.00221.

[67]

S. Schneider, E. Rusak, L. Eck, O. Bringmann, W. Brendel, and M. Bethge, “ Improving Robustness Against Common Corruptions by Covariate Shift Adaptation,” in Advances in Neural Information Processing Systems, Vol. 33 (2020), 11539-11551, https://doi.org/10.5555/3495724.3496692.

[68]

J. Zhang, L. Qi, Y. Shi, and Y. Gao, “ DomainAdaptor: A Novel Approach to Test-Time Adaptation,” in IEEE/CVF International Conference on Computer Vision (2023), 18925-18935, https://doi.org/10.1109/ICCV51070.2023.01739.

[69]

D. Hendrycks and T. Dietterich, “ Benchmarking Neural Network Robustness to Common Corruptions and Perturbations,” in International Conference on Learning Representations (2019), https://doi.org/10.48550/arXiv.1903.12261.

[70]

K. He, X. Zhang, S. Ren, and J. Sun, “ Deep Residual Learning for Image Recognition,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2016), 770-778, https://doi.org/10.1109/CVPR.2016.90.

[71]

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “ Densely Connected Convolutional Networks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2017), 2261-2269, https://doi.org/10.1109/CVPR.2017.243.

[72]

I. Gulrajani and D. Lopez-Paz, “ In Search of Lost Domain Generalization,” in International Conference on Learning Representations (2021), https://doi.org/10.48550/arXiv.2007.01434.

[73]

J. Guo, J. Zhao, C. Du, et al., “ Everything to the Synthetic: Diffusion-Driven Test-Time Adaptation via Synthetic-Domain Alignment,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2025), 30503-30513, https://doi.org/10.1109/CVPR52734.2025.02840.

[74]

H. Park, J. Hwang, S. Mun, S. Park, and J. Ok, “ MedBN: Robust Test-Time Adaptation Against Malicious Test Samples,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024), 5997-6007, https://doi.org/10.1109/CVPR52733.2024.00573.

[75]

D. Li, Y. Yang, Y. Z. Song, and T. M Hospedales, “ Deeper, Broader and Artier Domain Generalization,” in IEEE International Conference on Computer Vision (2017), 5542-5550, https://doi.org/10.1109/ICCV.2017.591.

[76]

D. Hendrycks, S. Basart, N. Mu, et al., “ The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization,” in IEEE/CVF International Conference on Computer Vision (2021), 8340-8349, https://doi.org/10.1109/ICCV48922.2021.00823.

[77]

Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, “ Reading Digits in Natural Images With Unsupervised Feature Learning,” in NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011), https://research.google/pubs/reading-digits-in-natural-images-with-unsupervised-feature-learning.

[78]

Y. Yang, C. Chen, and H. Huang, “ Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2026), 7957-7966, https://doi.org/10.48550/arXiv.2604.21772.

PDF (1807KB)

0

Accesses

0

Citation

Detail

Sections
Recommended

/

〈 〉