计算机科学 ›› 2022, Vol. 49 ›› Issue (3): 288-293.doi: 10.11896/jsjkx.210100156
许华杰1,2, 陈育1, 杨洋1, 秦远卓3
XU Hua-jie1,2, CHEN Yu1, YANG Yang1, QIN Yuan-zhuo3
摘要： 基于一致性的半监督学习方法通常使用简单的数据增强方法来实现对原始输入和扰动输入的一致性预测。在有标签数据的比例较低的情况下,该方法的效果难以得到保证。将监督学习中一些先进的数据增强方法扩展到半监督学习环境中,是解决该问题的思路之一。基于一致性的半监督学习方法MixMatch,提出了基于混合样本自动数据增强技术的半监督学习方法AutoMixMatch,在数据增强阶段采用自动数据增强技术,并在样本混合阶段提出了一种混合样本算法,用于提升对无标签样本的利用效果。通过图像分类方面的实验来测试所提方法的性能,在图像分类基准数据集中,所提方法在3种有标签样本比例下的分类效果均优于对比的几个主流半监督分类方法,验证了所提方法的有效性。此外,所提方法在有标签数据占训练数据比例极低(仅为0.05%)的情况下表现更好,在SVHN数据集上的实验结果表明,所提方法的分类错误率比MixMatch低30.17%。
中图分类号:
| [1]CHAPELLE O,SCHOLKOPF B,ZIEN A.Semi-supervisedlearning (chapelle,o.et al.,eds.;2006)[book reviews][J].IEEE Transactions on Neural Networks,2009,20(3):542. [2]LAINE S,AILA T.Temporal Ensembling for Semi-Supervised Learning[C]//Proceedings of the International Conference on Learning Representations (ICLR).2017. [3]TARVAINEN A,VALPOLA H.Mean teachers are better role models:Weight-averaged consistency targets improve semi-supervised deep learning results[C]//Advances in Neural Information Processing Systems.2017:1195-1204. [4]VERMA V,LAMB A,KANNALA J,et al.Interpolation Con-sistency Training for Semi-supervised Learning[C]//Procee-dings of the 28th International Joint Conference on Artificial Intelligence.AAAI Press,2019:3635-3641. [5]ZHANG H,CISSE M,DAUPHIN Y N,et al.mixup:BeyondEmpirical Risk Minimization[J].arXiv:1710.09412,2017. [6]XIE Q,DAI Z,HOVY E,et al.Unsupervised Data Augmentation for Consistency Training[J].arXiv:1904.12848,2019. [7]CUBUK E D,ZOPH B,SHLENS J,et al.RandAugment:Practical data augmentation with no separate search[J].arXiv:1909.13719,2019. [8]BERTHELOT D,CARLINI N,GOODFELLOW I,et al.Mix-Match:A Holistic Approach to Semi-Supervised Learning[J].arXiv:1905.02249,2019. [9]CUBUK E D,ZOPH B,MANE D,et al.AutoAugment:Lear-ning Augmentation Strategies From Data[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:113-123. [10]YUN S,HAN D,OH S J,et al.CutMix:Regularization Strategy to Train Strong Classifiers with Localizable Features[C]//International Conference on Computer Vision (ICCV).2019. [11]QIN Y,DING S F.Survey of Semi-supervised Clustering[J].Computer Science,2019,46(9):15-21. [12]ATHIWARATKUN B,FINZI M,IZMAILOV P,et al.There Are Many Consistent Explanations of Unlabeled Data:Why You Should Average[C]//Proceedings of the International Confe-rence on Learning Representations (ICLR).2019. [13]IZMAILOV P,PODOPRIKHIN D,GARIPOV T,et al.Averaging weights leads to wider optima and better generalization[J].arXiv:1803.05407,2018. [14]MIYATO T,MAEDA S,KOYAMA M,et al.Virtual adversa-rial training:a regularization method for supervised and semi-supervised learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,41(8):1979-1993. [15]FRENCH G,AILA T,LAINE S,et al.Semi-supervised semantic segmentation needs strong,high-dimensional perturbations[J].arXiv:1906.01916,2019. |
| [1] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
| [2] | 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 |
| [3] | 杜丽君, 唐玺璐, 周娇, 陈玉兰, 程建. 基于注意力机制和多任务学习的阿尔茨海默症分类 Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning 计算机科学, 2022, 49(6A): 60-65. https://doi.org/10.11896/jsjkx.201200072 |
| [4] | 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真. 一种基于支持向量机的主动度量学习算法 Active Metric Learning Based on Support Vector Machines 计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034 |
| [5] | 杨健楠, 张帆. 一种结合双注意力机制和层次网络结构的细碎农作物分类方法 Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure 计算机科学, 2022, 49(6A): 353-357. https://doi.org/10.11896/jsjkx.210200169 |
| [6] | 庞兴龙, 朱国胜. 基于半监督学习的网络流量分析研究 Survey of Network Traffic Analysis Based on Semi Supervised Learning 计算机科学, 2022, 49(6A): 544-554. https://doi.org/10.11896/jsjkx.210600131 |
| [7] | 朱旭东, 熊贇. 基于样本分布损失的图像多标签分类研究 Study on Multi-label Image Classification Based on Sample Distribution Loss 计算机科学, 2022, 49(6): 210-216. https://doi.org/10.11896/jsjkx.210300267 |
| [8] | 靳利贞, 李庆忠. 基于接缝一致性准则的结构纹理图像快速合成算法 Fast Structural Texture Image Synthesis Algorithm Based on Seam ConsistencyCriterion 计算机科学, 2022, 49(6): 262-268. https://doi.org/10.11896/jsjkx.210400039 |
| [9] | 王宇飞, 陈文. 基于DECORATE集成学习与置信度评估的Tri-training算法 Tri-training Algorithm Based on DECORATE Ensemble Learning and Credibility Assessment 计算机科学, 2022, 49(6): 127-133. https://doi.org/10.11896/jsjkx.211100043 |
| [10] | 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 |
| [11] | 张文轩, 吴秦. 基于多分支注意力增强的细粒度图像分类 Fine-grained Image Classification Based on Multi-branch Attention-augmentation 计算机科学, 2022, 49(5): 105-112. https://doi.org/10.11896/jsjkx.210100108 |
| [12] | 董琳, 黄丽清, 叶锋, 黄添强, 翁彬, 徐超. 人脸伪造检测泛化性方法综述 Survey on Generalization Methods of Face Forgery Detection 计算机科学, 2022, 49(2): 12-30. https://doi.org/10.11896/jsjkx.210900146 |
| [13] | 刘意, 毛莺池, 程杨堃, 高建, 王龙宝. 基于邻域一致性的异常检测序列集成方法 Locality and Consistency Based Sequential Ensemble Method for Outlier Detection 计算机科学, 2022, 49(1): 146-152. https://doi.org/10.11896/jsjkx.201000156 |
| [14] | 夏中, 向敏, 黄春梅. 基于CHBL的P2P视频监控网络分层管理机制 Hierarchical Management Mechanism of P2P Video Surveillance Network Based on CHBL 计算机科学, 2021, 48(9): 278-285. https://doi.org/10.11896/jsjkx.201200056 |
| [15] | 陈天荣, 凌捷. 基于特征映射的差分隐私保护机器学习方法 Differential Privacy Protection Machine Learning Method Based on Features Mapping 计算机科学, 2021, 48(7): 33-39. https://doi.org/10.11896/jsjkx.201200224 |
|
||
首页