计算机科学 ›› 2021, Vol. 48 ›› Issue (2): 217-223.doi: 10.11896/jsjkx.200700028
马闯1, 田青1,2, 孙赫阳1, 曹猛1, 马廷淮1
MA Chuang1, TIAN Qing1,2, SUN He-yang1, CAO Meng1, MA Ting-huai1
摘要: 无监督域适应(Unsupervised Domain Adaptation,UDA)是一类新兴的机器学习范式,其通过对源域知识在无标记目标域上的迁移利用,来促进目标域模型的训练。为建模源域与目标域之间的域分布差异,最大均值差异(Maximum Mean Discrepancy,MMD)建模被广泛应用,其对UDA的性能提升起到了有效的促进作用。然而,这些方法通常忽视了领域之间对应类规模与类分布等结构信息,因为目标域与源域的数据类规模与数据分布通常并非一致。为此,文中提出了一种基于跨域类和数据样本双重加权的无监督域适应模型(Sample weighted and Class weighted based Unsupervised Domain Adaptation Network,SCUDAN)。具体而言,一方面,通过源域类层面的适应性加权来调整源域类权重,以实现源域与目标域之间的类分布对齐;另一方面,通过目标域样本层面的适应性加权来调整目标域样本权重,以实现目标域与源域类中心的对齐。此外,文中还提出了一种CEM(Classification Expectation Maximization)优化算法,以实现对SCUDAN的优化求解。最后,通过对比实验和分析,验证了所提模型和算法的有效性。
中图分类号:
[1] LAWRENCE S,GILES C L,TSOI A C,et al.Face recognition:A convolutional neural-network approach[J].IEEE Transactions on Neural Networks,1997,8(1):98-113. [2] PAN S J,TSANG I W,KWOK J T,et al.Domain adaptation via transfer component analysis[J].IEEE Transactions on Neural Networks,2010,22(2):199-210. [3] DAUMÉ III H.Frustratingly easy domain adaptation[J].arXiv:0907.1815,2009. [4] SUN D M,ZHANG F F,MAO Q R.Label-Guided Domain Adaptation Method in Generative Adversarial Network for Facial Expression Recognition[J].Computer Engineering,2020,46(5):267-273,281. [5] WANG G,HAN H,SHAN S,et al.Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack Detection[J].IEEE Transactions on Information Forensics and Security,2020,16:56-69. [6] DUAN J M,MA X Z,LIU X.Path Tracking Method of Unmanned Vehicle Based on MFAPC[J].Computer Engineering,2019,45(6):6-11. [7] INOUE N,FURUTA R,YAMASAKI T,et al.Cross-domainweakly-supervised object detection through progressive domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:5001-5009. [8] CHEN C,GUO W B,LI Q Y.Adversarial domain adaptationwith self-attention in image classification[J].Computer Engineering and Science,2020,42(2):259-265. [9] SAITO K,KIM D,SCLAROFF S,et al.Semi-supervised domain adaptation via minimax entropy[C]//Proceedings of the IEEE International Conference on Computer Vision.2019:8050-8058. [10] DAUMÉ III H,KUMAR A,SAHA A.Frustratingly easy semi-supervised domain adaptation[C]//Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing.Association for Computational Linguistics,2010:53-59. [11] KUMAR A,SAHA A,DAUME H.Co-regularization basedsemi-supervised domain adaptation[C]//Advances in Neural Information Processing Systems.2010:478-486. [12] FERNANDO B,HABRARD A,SEBBAN M,et al.Unsuper-vised visual domain adaptation using subspace alignment[C]//Proceedings of the IEEE International Conference on Computer Vision.2013:2960-2967. [13] GANIN Y,LEMPITSKY V.Unsupervised domain adaptationby backpropagation[J].arXiv:1409.7495,2014. [14] JIANG J,ZHAI C X.Instance weighting for domain adaptation in NLP[C]//Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics.2007:264-271. [15] CHEN Q,LIU Y,WANG Z,et al.Re-weighted adversarial adaptation network for unsupervised domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7976-7985. [16] LIU J,ZHANG L.Optimal projection guided transfer hashingfor image retrieval[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019,33:8754-8761. [17] LONG M,WANG J,DING G,et al.Transfer feature learningwith joint distribution adaptation[C]//Proceedings of the IEEE International Conference on Computer Vision.2013:2200-2207. [18] DUAN L,XU D,TSANG I W H,et al.Visual event recognition in videos by learning from web data[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,34(9):1667-1680. [19] CAO Y,LONG M,WANG J.Unsupervised domain adaptation with distribution matching machines[C]//Thirty-Second AAAI Conference on Artificial Intelligence.2018. [20] LONG M,CAO Y,CAO Z,et al.Transferable representation learning with deep adaptation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,41(12):3071-3085. [21] LONG M,ZHU H,WANG J,et al.Deep transfer learning with joint adaptation networks[C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70.2017:2208-2217. [22] PINHEIRO P O.Unsupervised domain adaptation with similarity learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8004-8013. [23] ZHANG J,DING Z,LI W,et al.Importance weighted adversa-rial nets for partial domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8156-8164. [24] DZIUGAITE G K,ROY D M,GHAHRAMANI Z.Traininggenerative neural networks via maximum mean discrepancy optimization[J].arXiv:1505.03906,2015. [25] GONG B,GRAUMAN K,SHA F.Reshaping visual datasets for domain adaptation[C]//Advances in Neural Information Processing Systems.2013:1286-1294. [26] MOTIIAN S,PICCIRILLI M,ADJEROH D A,et al.Unifieddeep supervised domain adaptation and generalization[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:5715-5725. [27] KANG G,JIANG L,YANG Y,et al.Contrastive adaptation network for unsupervised domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:4893-4902. [28] WANG J,CHEN Y,HAO S,et al.Balanced distribution adaptation for transfer learning[C]//2017 IEEE InternationalConfe-rence on Data Mining (ICDM).IEEE,2017:1129-1134. [29] CELEUX G,GOVAERT G.A classification EM algorithm for clustering and two stochastic versions[J].Computational statistics & Data analysis,1992,14(3):315-332. [30] AL-JAWFI R.Handwriting Arabic character recognition LeNet using neural network[J].International Arab Journal of Information Technology,2009,6(3):304-309. [31] IANDOLA F N,HAN S,MOSKEWICZ M W,et al.Squeeze-Net:AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size[J].arXiv:1602.07360,2016. [32] ZHONG Z,JIN L,XIE Z.High performance offline handwritten chinese character recognition using googlenet and directional feature maps[C]//2015 13th International Conference on Document Analysis and Recognition (ICDAR).IEEE,2015:846-850. [33] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014. [34] LONG M,CAO Y,WANG J,et al.Learning transferable fea-tures with deep adaptation networks[J].arXiv:1502.02791,2015. [35] WESTON J,RATLE F,MOBAHI H,et al.Deep learning via semi-supervised embedding[M] ∥Neural networks:Tricks of the trade.Springer,Berlin,Heidelberg,2012:639-655. [36] TZENG E,HOFFMAN J,ZHANG N,et al.Deep domain confusion:Maximizing for domain invariance[J].arXiv:1412.3474,2014. [37] YAN H,DING Y,LI P,et al.Mind the class weight bias:Weighted maximum mean discrepancy for unsupervised domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2272-2281. |
[1] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
[2] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
[3] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
[4] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
[5] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
[6] | 张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036 |
[7] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
[8] | 刘月红, 牛少华, 神显豪. 基于卷积神经网络的虚拟现实视频帧内预测编码 Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network 计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179 |
[9] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
[10] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
[11] | 张嘉淏, 刘峰, 齐佳音. 一种基于Bottleneck Transformer的轻量级微表情识别架构 Lightweight Micro-expression Recognition Architecture Based on Bottleneck Transformer 计算机科学, 2022, 49(6A): 370-377. https://doi.org/10.11896/jsjkx.210500023 |
[12] | 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤. 不同数据增强方法对模型识别精度的影响 Influence of Different Data Augmentation Methods on Model Recognition Accuracy 计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210 |
[13] | 孙洁琪, 李亚峰, 张文博, 刘鹏辉. 基于离散小波变换的双域特征融合深度卷积神经网络 Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation 计算机科学, 2022, 49(6A): 434-440. https://doi.org/10.11896/jsjkx.210900199 |
[14] | 孙福权, 崔志清, 邹彭, 张琨. 基于多尺度特征的脑肿瘤分割算法 Brain Tumor Segmentation Algorithm Based on Multi-scale Features 计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217 |
[15] | 吴子斌, 闫巧. 基于动量的映射式梯度下降算法 Projected Gradient Descent Algorithm with Momentum 计算机科学, 2022, 49(6A): 178-183. https://doi.org/10.11896/jsjkx.210500039 |
|