山东大学学报 (工学版) ›› 2023, Vol. 53 ›› Issue (2): 102-108.doi: 10.6040/j.issn.1672-3961.0.2022.321
刘子一,崔超然*,孟凡安,林培光
LIU Ziyi, CUI Chaoran*, MENG Fan'an, LIN Peiguang
摘要： 为解决传统的领域自适应方法训练期间源域数据并不总是可用这一问题,提出一种无源多领域自适应方法,有效完成当存在领域漂移现象时的图像分类任务。通过最小化源域和目标域数据的批归一化统计量距离减小域之间的分布差异,解决因无法访问源域数据而无法显式对齐源域与目标域的问题;采用基于近邻聚合策略的伪标签分类器辅助生成更加准确的伪标签,提高模型预测的准确性;通过学习最优的融合权重,将多个自适应后的源域模型进行有效融合。构建基于批归一化统计量的无源多领域自适应模型。性能对比试验和消融试验结果表明,与多个基线模型相比,本研究方法预测准确性提高0.6%~3.7%。
中图分类号:
| [1] | LUO Y, ZHENG L, GUAN T, et al. Taking a closer look at domain shift: category-level adversaries for semantics consistent domain adaptation[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 2507-2516. |
| [2] | LIANG J, HU D P, FENG J S. Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation[C] //Proceedings of International Conference on Machine Learning. Vienna, Austria: PMLR, 2020: 6028-6039. |
| [3] | HUANG J X, GUAN D Y, XIAO A R, et al. Model adaptation:historical contrastive learning for unsupervised domain adaptation without source data[J]. Advances in Neural Information Processing Systems, 2021, 34: 3635-3649. |
| [4] | ISHII M, SUGIYAMA M. Source-free domain adaptation via distributional alignment by matching batch normalization statistics[EB/OL].(2022-04-24)[2022-09-25]. https://arxiv.org/abs/2101.10842. |
| [5] | LIANG J, HU D P, FENG J S. Domain adaptation with auxiliary target domain-oriented classifier[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 16632-16642. |
| [6] | GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communi-cations of the ACM, 2020, 63(11): 139-144. |
| [7] | LI J J, CHEN E P, DING Z M, et al. Cycle-consistent conditional adversarial transfer networks[C] //Proceedings of the 27th ACM International Conference on Multimedia. Nice, France: ACMM, 2019: 747-755. |
| [8] | HOFFMAN J, TZENG E, PARK T, et al. CyCADA:cycle-consistent adversarial domain adaptation[C] // International Conference on Machine Learning. Stockholm, Sweden: PMLR, 2018: 1989-1998. |
| [9] | KURMI V K, SUBRAMANIAN V K, NAMBOODIRI V P. Domain impression:a source data free domain adaptation method[C] //Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa, USA: IEEE, 2021: 615-625. |
| [10] | LI R, JIAO Q F, CAO W M, et al. Model adaptation:unsupervised domain adaptation without source data[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE, 2020: 9641-9650. |
| [11] | AHMED S M, RAYCHAUDHURI D S, PAUL S, et al. Unsupervised multi-source domain adaptation without access to source data[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 10103-10112. |
| [12] | DONG J H, FANG Z, LIU A J, et al. Confident anchor-induced multi-source free domain adaptation[J]. Advances in Neural Information Processing Systems, 2021, 34: 2848-2860. |
| [13] | HOFFMAN J, MOHRI M, ZHANG N. Algorithms and theory for multiple-source adaptation[J]. Advances in Neural Information Processing Systems, 2018, 31: 8246-8256. |
| [14] | ZHONG Z, ZHENG L, LUO Z M, et al. Invariance matters: exemplar memory for domain adaptive person re-identification[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 598-607. |
| [15] | GUO C, PLEISS G, SUN Y, et al. On calibration of modern neural networks[C] //Proceedings of International Conference on Machine Learning. Sydney, Australia: PMLR, 2017: 1321-1330. |
| [16] | LEE D H. Pseudo-label:the simple and efficient semi-supervised learning method for deep neural networks[C] //Proceedings of Workshop on Challenges in Representation Learning, ICML. Atlanta, USA: PMLR, 2013, 3(2): 896. |
| [17] | GONG B Q, SHI Y, SHA F, et al. Geodesic flow kernel for unsupervised domain adaptation[C] //2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA: IEEE, 2012: 2066-2073. |
| [18] | VENKATESWARA H, EUSEBIO J, CHAKRABORTY S, et al. Deep hashing network for unsupervised domain adaptation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 5018-5027. |
| [19] | YANG S, WANG Y, VAN DE WEIJER J, et al. Unsupervised domain adaptation without source data by casting a bait[EB/OL].(2021-10-29)[2022-09-25]. https://arxiv.org/abs/2010.12427. |
| [20] | KIM Y, CHO D, HAN K, et al. Domain adaptation without source data[J]. IEEE Transactions on Artificial Intelligence, 2021, 2(6): 508-518. |
| [1] | 徐芊芊,许倩,徐华畅,赵钰琳,徐凯,朱红. 基于CnViT的胶质瘤IDH1突变状态智能预测方法[J]. 山东大学学报 (工学版), 2023, 53(2): 127-134. |
|
