计算机科学 ›› 2021, Vol. 48 ›› Issue (6): 131-137.doi: 10.11896/jsjkx.210100008
刘昱彤1, 李鹏1,2,3, 孙云云4, 胡素君1
LIU Yu-tong1, LI Peng1,2,3, SUN Yun-yun4, HU Su-jun1
摘要： 相比传统的图像识别方法,利用深度网络可以提取到表征能力更好的特征,从而获得更好的识别效果。现实中任务提供的数据多为无标签数据或部分有标签数据,其为深度网络的学习带来了困难。而迁移学习的方法可以将从源域数据中学习到的知识迁移到目标任务的学习中,以解决有标签数据不足的问题。为了在迁移过程中减小源域和目标域间的图像数据差异,文中提出基于深度动态联合自适应网络的图像识别方法。对网络进行训练时,首先在多层网络结构中利用域间动态联合自适应方法完成针对性的数据分布自适应,然后利用熵最小化原则使学习的目标分类器穿过目标域的低密度区域,从而提高对目标域图像的识别精度。在2018年AI challenge比赛提供的24种植物病害数据集的3种迁移任务(g1－>g2,s1－>g2和s2－>g2)中,所提方法的准确率分别达到了97.27%,94.25%和93.66%,均优于其他算法。实验结果证明,文中提出的基于深度网络并使用动态联合自适应和熵最小化原则的学习框架能够准确识别图像。
中图分类号:
| [1]DONAHUE J,JIA Y,VINYALS O,et al.DeCAF:A Deep Convolutional Activation Feature for Generic Visual Recognition[C]//International Conference on Machine Learning.2013:647-655. [2]XAVIER G,BORDES A,BENGIO Y.Domain Adaptation for Large-Scale Sentiment Classification:A Deep Learning Approach[C]//Proceedings of International Conference on Machine Learning.Morgan Kaufmann Publishers Inc.,2011:513-520. [3]TZENG E,HOFFMAN J,ZHANG N,et al.Deep Domain Confusion:Maximizing for Domain Invariance[J].arXiv:1412.3474,2014. [4]YOSINSKI J,CLUNE J,BENGIO Y,et al.How transferableare features in deep neural networks?[C]//International Conference on Neural Information Processing Systems.Curran Associates Inc.,2014:3320-3328. [5]LONG M,CAO Y,WANG J,et al.Learning Transferable Features with Deep Adaptation Networks[C]//Proceedings of International Conference on Machine Learning.Morgan Kaufmann Publishers Inc.,2015:97-105. [6]LONG M,ZHU H,WANG J,et al.Deep Transfer Learningwith Joint Adaptation Networks[C]//International Conference on Machine Learning.2017:2208-2217. [7]HE K,ZHANG X,REN S,et al.Deep Residual Learning forImage Recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:770-778. [8]GRANDVALET Y,BENGIO Y O.Semi-supervised Learning by Entropy Minimization[C]//Proceedings of Advances in Neural Information Processing Systems.MIT Press,2004:529-536. [9]BALAKRISHNAN S,PONTIL M,FUKUMIZU K.Optimalkernel choice for large-scale two-sample tests[C]//Advances in Neural Information Processing Systems.2012:1205-1213. [10]TAN C,SUN F,KONG T,et al.A Survey on Deep TransferLearning[J].arXiv:1808.01974,2018. [11]SAENKO K,KULIS B,FRITZ M,et al.Adapting Visual Category Models to New Domains[M].Berlin,Heidelberg:Springer,2010:213-226. [12]COLLOBERT R,WESTON J,BOTTOU L,et al.Natural Language Processing (almost) from Scratch[J].Journal of Machine Learning Research,2011,12:2493-2537. [13]GHIFARY M,KLEIJN W B,ZHANG M.Domain AdaptiveNeural Networks for Object Recognition[C]//Proceedings of Pacific Rim International Conference on Artificial Intelligence.Berlin, Heidelberg:Springer,2014:898-904. [14]BORGWARDT K M,GRETTON A,RASCH M J,et al.In-tegrating structured biological data by Kernel Maximum Mean Discrepancy[J].Bioinformatics,2006,22(14):49-57. [15]LONG M,ZHU H,WANG J,et al.Unsupervised Domain Adaptation with Residual Transfer Networks[C]//Proceedings of Advances in Neural Information Processing Systems.MIT Press,2016:136-144. [16]SUN B,SAENKO K.Deep CORAL:Correlation Alignment for Deep Domain Adaptation[C]//Proceedings of European Confe-rence on Computer Vision.Berlin Heidelberg:Springer,2016:443-450. [17]ZELLINGER W,GRUBINGER T,LUGHOFER E,et al.Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning[J].arXiv:1702.08811,2017. [18]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative Adversarial Nets[C]//Advances in Neural Information Processing Systems.2014:2672-2680. [19]GANIN Y,USTINOVA E,AJAKAN H,et al.Domain-Adversarial Training of Neural Networks[J].The Journal of Machine Learning Research,2016,17(1):2096-3030. [20]CAO Z,LONG M,WANG J,et al.Partial Transfer Learning with Selective Adversarial Networks[J].arXiv:1707.07901,2017. [21]BEN-DAVID S,BLITZER J,CRAMMER K,et al.A theory of learning from different domains[J].Machine Learning,2010,79(1/2):151-175. [22]PAN S J,TSANG I W,KWOK J T,et al.Domain adaptation via transfer component analysis[J].IEEE Transactions on Neural Networks,2011,22(2):199-210. [23]LONG M,WANG J,DING G,et al.Transfer Joint Matching for Unsupervised Domain Adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2014:1410-1417. [24]LONG M,WANG J,DING G,et al.Transfer Feature Learning with Joint Distribution Adaptation[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision.IEEE,2013. [25]WANG J,CHEN Y,HAO S,et al.Balanced Distribution Adaptation for Transfer Learning[C]//The IEEE International Conference on Data Mining.IEEE,2017:1129-1134. [26]WANG J,FENG W,CHEN Y,et al.Visual Domain Adaptation with Manifold Embedded Distribution Alignment[C]//2018 ACM Multimedia Conference on Multimedia Conference.ACM,2018:402-410. [27]BEN-DAVID S,BLITZER J,CRAMMER K,et al.Analysis of Representations for Domain Adaptation[C]//International Conference on Neural Information Processing Systems.MIT Press,2007:137-144. [28]VAN DER M,HINTON G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9(2605):2579-2605. |
| [1] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
| [2] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
| [3] | 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 |
| [4] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
| [5] | 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 |
| [6] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
| [7] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
| [8] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
| [9] | 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 |
| [10] | 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 |
| [11] | 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 |
| [12] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
| [13] | 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 |
| [14] | 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018 |
| [15] | 周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044 |
|
||
首页