计算机科学 ›› 2022, Vol. 49 ›› Issue (6A): 93-99.doi: 10.11896/jsjkx.210500047
赵璐1, 袁立明2, 郝琨1
ZHAO Lu1, YUAN Li-ming2, HAO Kun1
摘要: 多示例学习是一种典型的弱监督学习框架,其样本示例包是一种集合类型数据,学习过程只需要包的粗粒度类别标记,能较好适应较难获得细粒度标记的应用问题。随着近几年深度学习的快速发展,深度多示例学习逐渐引起了研究者的兴趣。对多示例学习算法的研究进展进行综述,首先依据算法的层次结构将其划分为浅层模型和深度模型;然后对两类模型的相关算法进行回顾和总结,重点分析深度多示例学习模型在池化方式上的差别,并阐述以集合型数据为训练样本的模型所需满足的对称函数基本定理及其在深度多示例学习中的应用;最后通过实验对比分析不同算法的性能,且着重剖析其可解释性,并指明未来有待深入研究的问题。
中图分类号:
[1] SCHMIDHUBER J.Deep learning in neural networks:An overview[J].Neural Networks,2015,61:85-117. [2] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444. [3] LIU W,WANG Z,LIU X,et al.A survey of deep neural net-work architectures and their applications[J].Neurocomputing,2017,234:11-26. [4] LITJENS G,KOOI T,BEJNORDI B E,et al.A survey on deep learning in medical image analysis[J].Medical Image Analysis,2017,42:60-88. [5] ZHOU Z H.A brief introduction to weakly supervised learning[J].National Science Review,2018,5(1):44-53. [6] ZHOU Z H.Multi-instance Learning[R].Report of State Key Laboratory for Novel Software Technology at Nanjing Univer-sity,Nanjing,2006:1-13. [7] XU,Y,MO,T,FENG,Q,et al.Deep learning of feature representation with multiple instance learning for medical image analysis[C]//Proceedings of 2014 IEEE International Conference on Acoustics,Speech and Signal Processing.Italy,2014:1626-1630. [8] DIETTERICH T G,LATHROP R H,LOZANO-PÉREZ T.Solving the multiple instance problem with axis-parallel rectangles[J].Artificial Intelligence,1997,89(1/2):31-71. [9] AMORES J.Multiple instance classification:Review,taxonomyand comparative study[J].Artificial Intelligence,2013,201:81-105. [10] MARON O,LOZANO-PÉREZ T.A framework for multiple-instance learning[C]//Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems 10(NIPS '97).USA,1998:570-576. [11] ZHANG Q,GOLDMAN S A.EM-DD:An improved multiple-instance learning technique[C]//Proceedings of the 14th International Conference on Neural Information Processing Systems:Natural and Synthetic(NIPS'01).USA,2001:1073-1080. [12] ANDREWS S,TSOCHANTARIDIS I,HOFMANN T.Support vector machines for multiple-instance learning[C]//Advances in Neural Information Processing Systems.Canada,2002:577-584. [13] ZHOU Z H,ZHANG M L.Neural networks for multi-instance learning[R].Report of Computer Science Technology Department at Nanjing University,Nanjing,2002:1-14. [14] WANG J,ZUCKER J D.Solving multiple-instance problem:Alazy learning approach[C]//Proceedings of 17th International Conference on Machine Learning.USA,2000:1119-1126. [15] ZHANG M L,ZHOU Z H.Adapting RBF neural networks to multi-instance learning[J].Neural Processing Letters,2006,23(1):1-26. [16] GÄRTNER T,FLACH P A,KOWALCZYK A,et al.Multi-instance kernels[C]//Proceedings of International Conference on Machine Learning.Australia,2002:179-186. [17] ZHOU Z H,SUN Y Y,LI Y F.Multi-instance learning by treating instances as non-i.i.d.samples[C]//Proceedings of International Conference on Machine Learning.Canada,2009:1249-1256. [18] CHEN Y,WANG J Z.Image categorization by learning and reasoning with regions[J].Journal of Machine Learning Research,2004,5:913-939. [19] CHEN Y,BI J,WANG J Z.MILES:Multiple-instance learning via embedded instance selection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):1931-1947. [20] ZHOU Z H,ZHANG M L.Solving multi-instance problemswith classifier ensemble based on constructive clustering[J].Knowledge and Information Systems,2007,11(2):155-170. [21] ZHANG M L,ZHOU Z H.Multi-instance clustering with applications to multi-instance prediction[J].Applied Intelligence,2009,31(1):47-68. [22] CHEPLYGINA V,TAX D M,LOOG M.Multiple instancelearning with bag dissimilarities[J].Pattern Recognition,2015,48(1):264-275. [23] RAMON J,DE RAEDT L.Multi instance neural networks[C]//Proceedings of ICML-2000 Workshop on Attribute-Value and Relational Learning.USA,2000:53-60. [24] ZHANG M L,ZHOU Z H.Improve multi-instance neural networks through feature selection[J].Neural Processing Letters,2004,19(1):1-10. [25] WU J,YU Y,HUANG C,et al.Deep multiple instance learning for image classification and auto-annotation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.USA,2015:3460-3469. [26] WANG X,YAN Y,TANG,P,et al.Revisiting multiple instance neural networks[J].Pattern Recognition,2018,74:15-24. [27] ILSE M,TOMCZAK J M,WELLING M.Attention-based deep multiple instance learning[C]//Proceedings of International Conference on Machine Learning.Sweden,2018:2132-2141. [28] ZAHEER M,KOTTUR S,RAVANBAKHSH S,et al.Deepsets[C]//Advances in Neural Information Processing Systems.USA,2017:3391-3401. [29] SHI X S,XING F Y,XIE Y P,et al.Loss-based attention for deep multiple instance learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.USA,2020:5742-5749. [30] YAN Y,WANG X,GUO X,et al.Deep multi-instance learning with dynamic pooling[C]//Asian Conference on Machine Lear-ning.China,2018:662-677. [31] TU M,HUANG J,HE X,et al.Multiple instance learning with graph neural networks[J].arXiv:1906.04881,2019. [32] WANG X,YAN Y,TANG P,et al.Bag similarity network for deep multi-instance learning[J].Information Sciences,2019,504:578-588. [33] ZHOU Z H,FENG J.Deep forest:Towards an alternative todeep neural networks[C]//Proceedings of the 26th InternationalJoint Conference on Artificial Intelligence.USA,2017:3553-3559. [34] REN J,HOU B J,JIANG Y.Deep forest for multiple instance learning[J].Journal of Computer Research and Development,2019,56(8):1670-1676. [35] LAROCHELLE H,MURRAY I.The neural autoregressivedistribution estimator[C]//International Conference on Artificial Intelligence and Statistics.USA,2011:29-37. [36] VINYALS O,BENGIO S,KUDLUR M.Order matters:Se-quence to sequence for sets[J].arXiv:1511.06391,2015. [37] GENS R,DOMINGOS P M.Deep symmetry networks[C]//Advances in Neural Information Processing Systems.Canada,2014:2537-2545. [38] COHEN T,WELLING M.Group equivariant convolutional networks[C]//Proceedings of International Conference on Machine Learning.USA,2016:2990-2999. [39] RAVANBAKHSH S,SCHNEIDER J,POCZOS B.Equivariance through parameter-sharing[C]//International Conference on Machine Learning.Australia,2017:2892-2901. [40] FANG H,GUPTA S,IANDOLA F,et al.From captions to vi-sual concepts and back[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA,2015:1473-1482. [41] DIBA A,SHARMA V,PAZANDEH A,et al.Weakly supervised cascaded convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA,2017:5131-5139. [42] TANG P,WANG X,BAI X,et al.Multiple instance detection network with online instance classifier refinement[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA,2017:3059-3067. [43] ANGELIDIS S,LAPATA M.Multiple instance learning net-works for fine-grained sentiment analysis[J].Transactions of the Association for Computational Linguistics,2018,6:17-31. [44] LIN Y,SHEN S,LIU Z,et al.Neural relation extraction with selective attention over instances[C]//Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,Germany,2016:2124-2133. [45] E H H,ZHANG W J,XIAO S Q,et al.Survey of entity relationship extraction based on deep learning[J].Ruan Jian Xue Bao/Journal of Software,2019,30(6):1793-1818. [46] LITJENS G,KOOI T,BEJNORDI B E,et al.A survey on deep learning in medical image analysis[J].Medical Image Analysis,2017,42:60-88. [47] XU Y,MO T,FENG Q,et al.Deep learning of feature representation with multiple instance learning for medical image analysis[C]//International Conference on Acoustics,Speech and Signal Processing.Italy,2014:1626-1630. [48] KRAUS O Z,BA J L,FREY B J.Classifying and segmenting microscopy images with deep multiple instance learning[J].Bioinformatics,2016,32(12):52-59. [49] YAN Z,ZHAN Y,PENG Z,et al.Multi-instance deep learning:Discover discriminative local anatomies for bodypart recognition[J].IEEE Transactions on Medical Imaging,2016,35(5):1332-1343. [50] ZHU W,LOU Q,VANG Y S,et al.Deep multi-instance networks with sparse label assignment for whole mammogram classification[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Canada,2017:603-611. [51] LIU M,ZHANG J,ADELI E,et al.Landmark-based deep multi-instance learning for brain disease diagnosis[J].Medical Image Analysis,2018,43:157-168. [52] SONG W,REN D,YU J,et al.A new special video detection algorithm based on 3D convolution CoHOG and MIL[J].Chinese Journal of Computers,2019,42(1):149-163. [53] TSENG S Y,LI J,WANG Y,et al.Multiple Instance DeepLearning for Weakly Supervised Small-Footprint Audio Event Detection[J].arXiv:1712.09673,2017. [54] KONG Q,XU Y,WANG W,et al.Audio set classification with attention model:A probabilistic perspective[C]//International Conference on Acoustics,Speech and Signal Processing.Canada,2018:316-320. [55] YU C,BARSIM K S,KONG Q,et al.Multi-level attentionmodel for weakly supervised audio classification[J].arXiv:1803.02353v1,2018. [56] KONG Q,YU C,XU Y,et al.Weakly labelled audioset tagging with attention neural networks[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2019,27(11):1791-1802. [57] WANG Y,LI J,METZE F.A comparison of five multiple in-stance learning pooling functions for sound event detection with weak labeling[C]//International Conference on Acoustics,Speech and Signal Processing.UK,2019:31-35. [58] LIU X,JIAO L,ZHAO J,et al.Deep multiple instance learning-based spatial-spectral classification for PAN and MS imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2017,56(1):461-473. [59] URIOT T.Learning with sets in multiple instance regressionapplied to remote sensing[J].arXiv:1903.07745,2019. [60] OLIVA J B,DUBEY A,ZAHEER,M,et al.Transformation autoregressive networks[C]//International Conference on Machine Learning.Sweden,2018:3898-3907. |
[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] | 冷典典, 杜鹏, 陈建廷, 向阳. 面向自动化集装箱码头的AGV行驶时间估计 Automated Container Terminal Oriented Travel Time Estimation of AGV 计算机科学, 2022, 49(9): 208-214. https://doi.org/10.11896/jsjkx.210700028 |
[3] | 宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053 |
[4] | 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 |
[5] | 王明, 武文芳, 王大玲, 冯时, 张一飞. 生成链接树:一种高数据真实性的反事实解释生成方法 Generative Link Tree:A Counterfactual Explanation Generation Approach with High Data Fidelity 计算机科学, 2022, 49(9): 33-40. https://doi.org/10.11896/jsjkx.220300158 |
[6] | 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 |
[7] | 李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩. 基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究 Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network 计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094 |
[8] | 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 |
[9] | 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 |
[10] | 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 |
[11] | 张光华, 高天娇, 陈振国, 于乃文. 基于N-Gram静态分析技术的恶意软件分类研究 Study on Malware Classification Based on N-Gram Static Analysis Technology 计算机科学, 2022, 49(8): 336-343. https://doi.org/10.11896/jsjkx.210900203 |
[12] | 何强, 尹震宇, 黄敏, 王兴伟, 王源田, 崔硕, 赵勇. 基于大数据的进化网络影响力分析研究综述 Survey of Influence Analysis of Evolutionary Network Based on Big Data 计算机科学, 2022, 49(8): 1-11. https://doi.org/10.11896/jsjkx.210700240 |
[13] | 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 |
[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 |
|