计算机科学 ›› 2021, Vol. 48 ›› Issue (6A): 357-363.doi: 10.11896/jsjkx.201000030
吴兰, 王涵, 李斌全
WU Lan, WANG Han, LI Bin-quan
摘要: 无监督域自适应方法通过源域标签数据学习到的知识对目标域无标签数据进行分类,成为目前迁移学习中解决两个域特征对齐的主流方法。针对现实中存在已标签数据量少且质量不高造成提取的特征不完备的情况,文中提出了基于自监督任务最优选择的无监督域自适应方法。为使特征具有更强的语义信息,在两个域未标记数据上使用了多个自监督任务;此外,针对进行自监督任务时的易混淆特征,提出了一种新的智能组合优化策略自适应地选择有效特征;最后通过两个域沿着任务相关方向靠近使得源域标记数据训练的分类器能够更好地推广到目标域。仿真实验在公开的6个基准数据集上分别从分类精度、训练集数据使用量、自监督任务使用效果3个方面进行了对比分析。实验结果表明,所提方法在3个方面上的表现都优于现有的先进方法,使用相同数据集时分类精度提高8%;在相同的分类精度要求下,所用数据量减少12%;与单个自监督任务对比时精度提高了11%。
中图分类号:
[1] LIU H,CAO Z J,LONG M S,et al.Separate toAdapt:Open Set Domain Adaptation via Progressive Separation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2019:2927-2936. [2] SAITO K,KIM D,SCLAROFF S,et al.Semi-Supervised Do-main Adaptation via Minimax Entropy[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).2019:8050-8058. [3] TAN S H,JIAO J N,ZHENG W S.Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration[C]//Proceedings of theIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2019:5394-5403. [4] BOUSMALIS K,SILBERMAN N,DOHAN D,et al.Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017:3722-3731. [5] TZENG E,HOFFMAN J,SAENKO K,et al.Adversarial Discriminative Domain Adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017:7167-7176. [6] HOFFMAN J,TZENG E,PARK T,et al.CyCADA:Cycle-Consistent adversarial domain adaptation[J].arXiv:1711.03213,2017. [7] SAITO K,USHIKU Y,HARADA T,et al.Adversarial dropout regularization[J].arXiv:1711.01575,2017. [8] SHU R,BUI H H,NARUI H,et al.A DIRT-T approach to un-supervised domain adaptation[J].arXiv:1802.08735,2018. [9] BOUSMALIS K,TRIGEORGIS G,SILBERMAN N,et al.Domain Separation Networks[C]//Advances in Neural Information Processing Systems.2016. [10] SUN Y,TZENG E,DARRELL T,et al.Unsupervised domain adaptation through self-supervision[J].arXiv:1909.11825,2019. [11] GHIFARY M,KLEIJN W B,ZHANG M J,et al.Deep recon-struction-classifification networks for unsupervised domain adaptation[C]//European Conference on Computer Vision.2016:597-613. [12] SAITO K,USHIKU Y,HARADA T.Asymmetric tri-training for unsupervised domain adaptation[J].arXiv:1702.08400,2017. [13] HAEUSSER P,FRERIX T,MORDVINTSEV A,et al.Associative Domain Adaptation[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV).2017:2765-2773. [14] ZADROZNY B.Learning and Evaluating Classifiers Under Sample Selection Bias[C]//Proceedings of theInternational Conference on Machine Learning(ICML).Canada:ICML,2004:114-122. [15] CASEIRO R,HENRIQUES J F,MARTINS P,et al.Unsupervised Domain Adaptation by Sampling Subspaces Along the Spline Flow[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).USA:IEEE,2015:3846-3854. [16] TSAI Y,YEH Y R,WANG F Y C.Learning Cross-DomainLandmarks for Heterogeneous Domain Adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).USA:IEEE,2016:5081-5090. [17] DAI W,CHEN Y,XUE G R,et al.Translated Learning:Transfer Learning Across Different Feature Spaces[C]//Proceedings of theAnnual Conference on Neural Information Processing Systems (NIPS).Canada:NIPS,2008:353-360. [18] KANG U L,JIANG L,YANG Y,et al.Contrastive Adaptation Network for Unsupervised Domain Adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:4893-4902. [19] PAN Y W,YAO T,LI Y H,et al.Transferrable PrototypicalNetworks for Unsupervised Domain Adaptation[J].arXiv:1904.11227,2019. [20] KANG G L,JIANG L,YANG Y,et al.Contrastive Adaptation Network for Unsupervised Domain Adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2019:4893-4902. [21] SENER O,SONG H O,SAXENA A,et al.Learning Transferrable Representations for Unsupervised Domain Adaptation.Domain Separation Networks[C]//Advances in Neural Information Processing Systems.2016. [22] GANIN Y,USTINOVA E,AJAKAN H,et al.Domain-Adversarial Training of Neural Networks[C]//Journal of Machine Learning Research.2016:1-35. [23] GANIN Y,LEMPISKY V.Unsupervised domain adaptation by backpropagation[C]//International Conference on Machine Learning.2015:1180-1189. [24] ZHANG R,ISOLA P,EFROS A A.Colorful image colorization[J].European Conference on Computer Vision,2016,9907:649-666. [25] LARSSON G,MAIRE M,SHAKHNAROVICH G.Learningrepresentationsfor automatic colorization[J].European Confe-rence on Computer Vision,2016,9908:577-593. [26] VONDRICK C,SHRIVASTAVA A,FATHI A,et al.Tracking Emerges by Colorizing Videos[C]//Proceedings of the Euro-pean Conference on Computer Vision.2018:391-408. [27] NOROOZI M,FAVARO P.Unsupervisedlearning of visual representations by solving jigsaw puzzles[J].European Conference on Computer Vision,2016,9910:69-84. [28] DOERSCH C,GUPTA A,EFROS A A.Unsupervised visualrepresentation learning by context prediction[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:1422-1430. [29] JENNI I,FAVARO P.Self-Supervised Feature Learning byLearning to Spot Artifacts[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:2733-2742. [30] GIDARIS S,SINGH P,KOMODAKIS N.Unsupervised Representation learning by predicting image rotations[J].arXiv:1803.07728,2018. [31] PATHAK D,KRAHENBUHL P,DONAHUE J,et al.Contextencoders:Feature learning by inpainting[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2016:2536-2544. [32] GIDARIS S,SINGH P,KOMODAKIS N.Unsupervised representation learning by predicting image rotations[J].arXiv:1803.07728,2018. |
[1] | 方义秋, 张震坤, 葛君伟. 基于自注意力机制和迁移学习的跨领域推荐算法 Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning 计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011 |
[2] | 闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042 |
[3] | 王君锋, 刘凡, 杨赛, 吕坦悦, 陈峙宇, 许峰. 基于多源迁移学习的大坝裂缝检测 Dam Crack Detection Based on Multi-source Transfer Learning 计算机科学, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124 |
[4] | 郭亮, 杨兴耀, 于炯, 韩晨, 黄仲浩. 基于注意力机制和门控网络相结合的混合推荐系统 Hybrid Recommender System Based on Attention Mechanisms and Gating Network 计算机科学, 2022, 49(6): 158-164. https://doi.org/10.11896/jsjkx.210500013 |
[5] | 彭云聪, 秦小林, 张力戈, 顾勇翔. 面向图像分类的小样本学习算法综述 Survey on Few-shot Learning Algorithms for Image Classification 计算机科学, 2022, 49(5): 1-9. https://doi.org/10.11896/jsjkx.210500128 |
[6] | 谭珍琼, 姜文君, 任演纳, 张吉, 任德盛, 李晓鸿. 基于二分图的个性化学习任务分配 Personalized Learning Task Assignment Based on Bipartite Graph 计算机科学, 2022, 49(4): 269-281. https://doi.org/10.11896/jsjkx.210500125 |
[7] | 左杰格, 柳晓鸣, 蔡兵. 基于图像分块与特征融合的户外图像天气识别 Outdoor Image Weather Recognition Based on Image Blocks and Feature Fusion 计算机科学, 2022, 49(3): 197-203. https://doi.org/10.11896/jsjkx.201200263 |
[8] | 张舒萌, 余增, 李天瑞. 跨领域文本的可迁移情绪分析方法 Transferable Emotion Analysis Method for Cross-domain Text 计算机科学, 2022, 49(3): 218-224. https://doi.org/10.11896/jsjkx.210400034 |
[9] | 潘志豪, 曾碧, 廖文雄, 魏鹏飞, 文松. 基于交互注意力图卷积网络的方面情感分类 Interactive Attention Graph Convolutional Networks for Aspect-based Sentiment Classification 计算机科学, 2022, 49(3): 294-300. https://doi.org/10.11896/jsjkx.210100180 |
[10] | 邵海琳, 季怡, 刘纯平, 徐云龙. 基于增强特征金字塔网络的场景文本检测算法 Scene Text Detection Algorithm Based on Enhanced Feature Pyramid Network 计算机科学, 2022, 49(2): 248-255. https://doi.org/10.11896/jsjkx.201100072 |
[11] | 李星燃, 张立言, 姚树婧. 结合特征融合和注意力机制的微表情识别方法 Micro-expression Recognition Method Combining Feature Fusion and Attention Mechanism 计算机科学, 2022, 49(2): 4-11. https://doi.org/10.11896/jsjkx.210900028 |
[12] | 侯宏旭, 孙硕, 乌尼尔. 蒙汉神经机器翻译研究综述 Survey of Mongolian-Chinese Neural Machine Translation 计算机科学, 2022, 49(1): 31-40. https://doi.org/10.11896/jsjkx.210900006 |
[13] | 李达, 雷迎科, 张海川. 基于LTE网络的室外指纹定位 Outdoor Fingerprint Positioning Based on LTE Networks 计算机科学, 2021, 48(6A): 404-409. https://doi.org/10.11896/jsjkx.200700170 |
[14] | 熊朝阳, 王婷. 基于卷积神经网络的建筑构件图像识别 Image Recognition for Building Components Based on Convolutional Neural Network 计算机科学, 2021, 48(6A): 51-56. https://doi.org/10.11896/jsjkx.200500122 |
[15] | 刘昱彤, 李鹏, 孙云云, 胡素君. 基于深度动态联合自适应网络的图像识别方法 Image Recognition with Deep Dynamic Joint Adaptation Networks 计算机科学, 2021, 48(6): 131-137. https://doi.org/10.11896/jsjkx.210100008 |
|