解耦表征学习研究进展

doi:10.11772/j.issn.1001-9081.2021060895

《计算机应用》唯一官方网站 ›› 2021, Vol. 41 ›› Issue (12): 3409-3418.DOI: 10.11772/j.issn.1001-9081.2021060895

所属专题：综述；第十八届中国机器学习会议(CCML 2021)

• 第十八届中国机器学习会议(CCML 2021) • 下一篇

解耦表征学习研究进展

成科扬¹^,²(), 孟春运¹, 王文杉², 师文喜²^,³, 詹永照¹

^1.江苏大学计算机科学与通信工程学院，江苏镇江 212013
^2.社会安全风险感知与防控大数据应用国家工程实验室（中国电子科学研究院），北京 100041
^3.新疆联海创智信息科技有限公司，乌鲁木齐 830011

收稿日期:2021-05-12 修回日期:2021-06-21 接受日期:2021-06-25 发布日期:2021-08-20 出版日期:2021-12-10
通讯作者: 成科扬
作者简介:孟春运（1994—），男，江苏扬州人，硕士研究生，主要研究方向：计算机视觉、模式识别
王文杉（1994—），女，湖北武汉人，硕士，主要研究方向：统计分析、机器学习
师文喜（1988—），男，北京人，博士，主要研究方向：大数据分析、智慧安防
詹永照（1962—），男，福建尤溪人，教授，博士生导师，博士，主要研究方向：多媒体、人工智能。
基金资助:
国家自然科学基金资助项目(61972183);社会安全风险感知与防控大数据应用国家工程实验室主任基金资助项目

Research advances in disentangled representation learning

Keyang CHENG¹^,²(), Chunyun MENG¹, Wenshan WANG², Wenxi SHI²^,³, Yongzhao ZHAN¹

^1.School of Computer Science and Communication Engineering，Jiangsu University，Zhenjiang Jiangsu 212013，China
^2.National Engineering Laboratory of Big Data Application for Social Security Risk Perception and Prevention by Big Data （China Academy of Electronic and Information Technology），Beijing 100041，China
^3.Xinjiang Lianhai Chuangzhi Information Technology Company Limited，Urumqi Xinjiang 830011，China

Received:2021-05-12 Revised:2021-06-21 Accepted:2021-06-25 Online:2021-08-20 Published:2021-12-10
Contact: Keyang CHENG
About author:MENG Chunyun， born in 1994， M. S. candidate. His research interests include computer vision， pattern recognition.
WANG Wenshan， born in 1994， M. S. Her research interests include statistical analysis， machine learning.
SHI Wenxi， born in 1988， Ph. D. His research interests include big data analysis， smart security.
ZHAN Yongzhao， born in 1962， Ph. D.， professor. His research interest include multimedia， artificial intelligence.
Supported by:
the National Natural Science Foundation of China(61972183);the Director Foundation of National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data

摘要/Abstract

摘要：

解耦表征学习旨在对影响数据形态的关键因素进行建模，使得某一关键因素的变化仅仅引起数据在某项特征上的变化，而其他的特征不受影响，这有利于应对机器学习在模型可解释性、对象生成和操作以及零样本学习等问题上的挑战，因此解耦表征学习一直是机器学习领域的一个研究热点。从解耦表征学习的历史与动机入手，对解耦表征学习的研究现状以及应用进行归纳总结，分析了解耦表征所具有的不变性、复用性等特性，介绍了基于生成解耦表征变差因素的研究、基于流形相互作用解耦表征变差因素的研究、基于对抗性训练解耦表征变差因素的研究，以及一种变分自编码器β-VAE的研究等最新研究动态。同时，阐述了解耦表征学习的典型应用，并对未来的研究方向作出了展望。

关键词: 解耦学习, 表征学习, 变分推断, 可解释性, 机器学习, 自编码器, 变差因素, 复用性

Abstract:

The purpose of disentangled representation learning is to model the key factors that affect the form of data， so that the change of a key factor only causes the change of data on a certain feature， while the other features are not affected. It is conducive to face the challenge of machine learning in model interpretability， object generation and operation， zero-shot learning and other issues. Therefore， disentangled representation learning always be a research hotspot in the field of machine learning. Starting from the history and motives of disentangled representation learning， the research status and applications of disentangled representation learning were summarized， the invariance， reusability and other characteristics of disentangled representation learning were analyzed， and the research on the factors of variation via generative entangling， the research on the factors of variation with manifold interaction， and the research on the factors of variation using adversarial training were introduced， as well as the latest research trends such as a Variational Auto-Encoder （VAE） named β-VAE were introduced. At the same time， the typical applications of disentangled representation learning were shown， and the future research directions were prospected.

Key words: disentangled learning, representation learning, variational inference, interpretability, machine learning, auto-encoder, factors of variation, reusability

中图分类号:

TP391

成科扬, 孟春运, 王文杉, 师文喜, 詹永照. 解耦表征学习研究进展[J]. 计算机应用, 2021, 41(12): 3409-3418.

Keyang CHENG, Chunyun MENG, Wenshan WANG, Wenxi SHI, Yongzhao ZHAN. Research advances in disentangled representation learning[J]. Journal of Computer Applications, 2021, 41(12): 3409-3418.

图/表 3

图1 面部图像中建模姿势和身份变化的方法

Fig. 1 Approach for modeling pose and identity variations in face images

图2 FactorVAE的架构

Fig. 2 Architecture of FactorVAE

图3 图像到图像的转换

Fig. 3 Image-to-image translation

参考文献 82

1	BENGIO Y， COURVILLE A， VINCENT P. Representation learning： a review and new perspectives［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2013， 35（8）： 1798-1828. 10.1109/tpami.2013.50
2	胡铭菲，刘建伟，左信. 深度生成模型综述［J/OL］. 自动化学报. （2020-09-21）［2020-09-27］.，
	LIU J W， ZUO X. Survey on deep generative models［J/OL］. Acta Automatica Sinica. （2020-09-21）［2020-09-27］..
3	GIBSON J J. The Ecological Approach to Visual Perception： Classic Edition［M］. Hove， East Sussex： Psychology Press， 1979：89-90. 10.4324/9781315740218
4	DODWELL P C. The Lie transformation group model of visual perception［J］. Perception and Psychophysics， 1983， 34（1）： 1-16. 10.3758/bf03205890
5	LOWE D G. Object recognition from local scale-invariant features［C］// Proceedings of the 7th IEEE International Conference on Computer Vision. Piscataway： IEEE， 1999： 1150-1157. 10.1109/iccv.1999.790410
6	DALAL N， TRIGGS B. Histograms of oriented gradients for human detection［C］// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2005： 886-893. 10.1109/cvpr.2005.177
7	SUNDARAMOORTHI G， PETERSEN P， VARADARAJAN V S， et al. On the set of images modulo viewpoint and contrast changes［C］// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2009： 832-839. 10.1109/cvpr.2009.5206704
8	KRIZHEVSKY A， SUTSKEVER I， HINTON G E. ImageNet classification with deep convolutional neural networks［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc. ， 2012， 25： 1097-1105.
9	YAO X， NEWSON A， GOUSSEAU Y， et al. A latent transformer for disentangled face editing in images and videos［C］// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 13789-13798. 10.1109/icip42928.2021.9506060
10	LECUN Y， JACKEL L D， BOSER B， et al. Handwritten digit recognition： applications of neural network chips and automatic learning［J］. IEEE Communications Magazine， 1989， 27（11）： 41-46. 10.1109/35.41400
11	WANG H， ULLAH M M， KLÄSER A， et al. Evaluation of local spatio-temporal features for action recognition［C］// Proceedings of the 2009 British Machine Vision Conference. Durham： BMVA Press， 2009： No.143. 10.5244/c.23.124
12	COURVILLE A， BERGSTRA J， BENGIO Y. A spike and slab restricted Boltzmann machine［C］// Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. New York： JMLR.org， 2011： 233-241.
13	KOHONEN T. Emergence of invariant-feature detectors in the adaptive-subspace self-organizing map［J］. Biological Cybernetics， 1996， 75（4）： 281-291. 10.1007/s004220050295
14	HYVÄRINEN A， HOYER P. Emergence of phase- and shift-invariant features by decomposition of natural images into independent feature subspaces［J］. Neural Computation， 2000， 12（7）： 1705-1720. 10.1162/089976600300015312
15	KAVUKCUOGLU K， RANZATO M， FERGUS R， et al. Learning invariant features through topographic filter maps［C］// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2009： 1605-1612. 10.1109/cvpr.2009.5206545
16	RANZATO M， HINTON G E. Modeling pixel means and covariances using factorized third-order Boltzmann machines［C］// Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2010： 2551-2558. 10.1109/cvpr.2010.5539962
17	HIGGINS I， AMOS D， PFAU D， et al. Towards a definition of disentangled representations［EB/OL］. （2018-12-05）［2020-09-27］..
18	DAHL G E， RANZATO M， MOHAMED A R， et al. Phone recognition with the mean-covariance restricted Boltzmann machine［C］// Proceedings of the 23rd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2010： 469-477.
19	SEIDE F， LI G， YU D. Conversational speech transcription using context-dependent deep neural networks［C］// Proceedings of the 12th Annual Conference of the International Speech Communication Association. Grenoble： ISCA， 2011： 437-440. 10.21437/interspeech.2011-169
20	CHARTSIAS A， JOYCE T， PAPANASTASIOU G， et al. Disentangled representation learning in cardiac image analysis［J］. Medical Image Analysis， 2019， 58： No.101535. 10.1016/j.media.2019.101535
21	DAHL G E， YU D， DENG L， et al. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition［J］. IEEE Transactions on Audio， Speech， and Language Processing， 2012， 20（1）： 30-42. 10.1109/tasl.2011.2134090
22	许世斌，高子淑. 基于共性假设的零样本生成模型［J］. 计算机应用与软件， 2020， 37（8）：177-181. 10.3969/j.issn.1000-386x.2020.08.031
	XU S B， GAO Z S. A generative model for zero shot learning based on common hypothesis［J］. Computer Applications and Software， 2020， 37（8）：177-181. 10.3969/j.issn.1000-386x.2020.08.031
23	王德文，魏波涛. 基于孪生变分自编码器的小样本图像分类方法［J］. 智能系统学报， 2021， 16（2）： 254-262. 10.11992/tis.201906022
	WANG D W， WEI B T. A small-sample image classification method based on a Siamese variational auto-encoder［J］. CAAI Transactions on Intelligent Systems， 2021， 16（2）： 254-262. 10.11992/tis.201906022
24	BOULANGER-LEWANDOWSKI N， BENGIO Y， VINCENT P. Modeling temporal dependencies in high-dimensional sequences： application to polyphonic music generation and transcription［C］// Proceedings of the 29th International Conference on International Conference on Machine Learning. Madison， WI： Omnipress ， 2012： 1881-1888. 10.1109/icassp.2013.6638244
25	HAMEL P， LEMIEUX S， BENGIO Y， et al. Temporal pooling and multiscale learning for automatic annotation and ranking of music audio［C］// Proceedings of the 12th International Society for Music Information Retrieval Conference. ［S.l.］： ISMIR， 2011： 729-734. http://dx.doi.org/
26	HINTON G E. Learning distributed representations of concepts［M］// MORRIS R G M， Parallel Distributed Processing： Implications for Psychology and Neurobiology. Oxford： Oxford University Press， 1989： 46-61.
27	BENGIO Y. Neural net language models［J］. Scholarpedia， 2008， 3（1）： No.3881. 10.4249/scholarpedia.3881
28	COLLOBERT R， WESTON J， BOTTOU L， et al. Natural language processing （almost） from scratch［J］. Journal of Machine Learning Research， 2011， 12： 2493-2537.
29	BENGIO Y， COURVILLE A， VINCENT P. Representation learning： a review and new perspectives［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2013， 35（8）： 1798-1828. 10.1109/tpami.2013.50
30	TANG Y B， TANG Y X， ZHU Y Y， et al. A disentangled generative model for disease decomposition in chest X-rays via normal image synthesis［J］. Medical Image Analysis， 2021， 67： No.101839. 10.1016/j.media.2020.101839
31	屠恩美，杨杰. 半监督学习理论及其研究进展概述［J］. 上海交通大学学报， 2018， 52（10）：1280-1291. 10.16183/j.cnki.jsjtu.2018.10.017
	TU E M， YANG J. A review of semi-supervised learning theories and recent advances［J］. Journal of Shanghai Jiao Tong University， 2018， 52（10）：1280-1291. 10.16183/j.cnki.jsjtu.2018.10.017
32	HAO Z F， LV D， LI Z J， et al. Semi-supervised disentangled framework for transferable named entity recognition［J］. Neural Networks， 2021， 135： 127-138. 10.1016/j.neunet.2020.11.017
33	LI H L， WAN R J， WANG S Q， et al. Unsupervised domain adaptation in the wild via disentangling representation learning［J］. International Journal of Computer Vision， 2021， 129（2）： 267-283. 10.1007/s11263-020-01364-5
34	COURVILLE A， BERGSTRA J， BENGIO Y. Unsupervised models of images by spike-and-slab RBMs［C］// Proceedings of the 28th International Conference on International Conference on Machine Learning. Madison， WI： Omnipress， 2011： 1145-1152.
35	DESJARDINS G， COURVILLE A， BENGIO Y. Disentangling factors of variation via generative entangling［EB/OL］. （2012-10-19）［2021-04-22］..
36	HINTON G E， KRIZHEVSKY A， WANG S D. Transforming auto-encoders［C］// Proceedings of the 2011 International Conference on Artificial Neural Networks， LNCS6791. Berlin： Springer， 2011： 44-51.
37	MEMISEVIC R， HINTON G E. Learning to represent spatial transformations with factored higher-order Boltzmann machines［J］. Neural Computation， 2010， 22（6）： 1473-1492. 10.1162/neco.2010.01-09-953
38	TENENBAUM J B， DE SILVA V， LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction［J］. Science， 2000， 290（5500）： 2319-2323. 10.1126/science.290.5500.2319
39	RIFAI S， VINCENT P， MULLER X， et al. Contractive auto-encoders： explicit invariance during feature extraction［C］// Proceedings of the 28th International Conference on International Conference on Machine Learning. Madison， WI： Omnipress， 2011： 833-840. 10.1007/978-3-642-23783-6_41
40	TANG Y C， SALAKHUTDINOV R， HINTON G. Tensor analyzers［C］// Proceedings of the 30th International Conference on Machine Learning. New York： JMLR.org， 2013： 163-171.
41	卫亮亮. 基于流结构变分推断的深度生成模型研究［D］. 保定：河北大学， 2019. 10.25221/fee.376.2
	WEI L L. Research on deep generative models based on variational inference of flow structure［D］. Baoding： Hebei University， 2019. 10.25221/fee.376.2
42	BENGIO Y， MESNIL G， DAUPHIN Y， et al. Better mixing via deep representations［C］// Proceedings of the 30th International Conference on Machine Learning. New York： JMLR.org， 2013： 552-560. 10.1007/978-3-642-36657-4_1
43	REED S， SOHN K， ZHANG Y T， et al. Learning to disentangle factors of variation with manifold interaction［C］// Proceedings of the 31st International Conference on Machine Learning. New York： JMLR.org， 2014： 1431-1439.
44	BENGIO Y. Learning deep architectures for AI［J］. Foundations and Trends in Machine Learning， 2009， 2（1）： 1-127. 10.1561/2200000006
45	LI X Q， CHEN L B， WANG L， et al. SCGAN： disentangled representation learning by adding similarity constraint on generative adversarial nets［J］. IEEE Access， 2019， 7： 147928-147938. 10.1109/access.2018.2872695
46	MATHIEU M， ZHAO J B， SPRECHMANN P， et al. Disentangling factors of variation in deep representation using adversarial training［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2016： 5047-5055.
47	杨晨曦，左劼，孙频捷. 基于自编码器的零样本学习方法研究进展［J］. 现代计算机， 2020（1）：48-52. 10.3969/j.issn.1007-1423.2020.01.011
	YANG C X， ZUO J， SUN P J. Research progress of zero-shot learning method based on autoencoder［J］. Modern Computer， 2020（1）：48-52. 10.3969/j.issn.1007-1423.2020.01.011
48	王路，李寿山. 基于变分自编码器的问题识别方法［J］. 郑州大学学报（理学版）， 2019， 51（3）：79-84. 10.18653/v1/2020.emnlp-main.307
	WANG L， LI S S. Question detection method based on variational auto-encoder［J］. Journal of Zhengzhou University （Natural Science Edition）， 2019， 51（3）：79-84. 10.18653/v1/2020.emnlp-main.307
49	翟正利，梁振明，周炜，等. 变分自编码器模型综述［J］. 计算机工程与应用， 2019， 55（3）：1-9. 10.3778/j.issn.1002-8331.1810-0284
	ZHAI Z L， LIANG Z M， ZHOU W， et al. Research overview of variational auto-encoders models［J］. Computer Engineering and Applications， 2019， 55（3）：1-9. 10.3778/j.issn.1002-8331.1810-0284
50	KINGMA D P， WELLING M. Auto-encoding variational Bayes［EB/OL］. （2014-05-01）［2020-09-27］.. 10.1561/9781680836233
51	HIGGINS I， MATTHEY L， PAL A， et al. β-VAE： learning basic visual concepts with a constrained variational framework［EB/OL］. ［2020-09-27］..
52	HIGGINS I， SONNERAT N， MATTHEY L， et al. SCAN： learning abstract hierarchical compositional visual concepts［EB/OL］. （2018-06-06）［2020-09-27］..
53	HIGGINS I， CHANG L， LANGSTON V， et al. Unsupervised deep learning identifies semantic disentanglement in single inferotemporal face patch neurons［J］. Nature Communications， 2021， 12（1）： 1-14. 10.1038/s41467-021-26751-5
54	BURGESS C P， HIGGINS I， PAL A， et al. Understanding disentangling in β-VAE［EB/OL］. （2018-04-10）［2020-09-27］..
55	KIM H， MNIH A. Disentangling by factorising［C］// Proceedings of the 35th International Conference on Machine Learning. New York： JMLR.org， 2018： 2649-2658.
56	PATACCHIOLA M， FOX-ROBERTS P， ROSTEN E. Y-Autoencoders： disentangling latent representations via sequential encoding［J］. Pattern Recognition Letters， 2020， 140： 59-65. 10.1016/j.patrec.2020.09.025
57	HIGGINS I， PAL A， RUSU A， et al. DARLA： improving zero-shot transfer in reinforcement learning［C］// Proceedings of the 34th International Conference on Machine Learning. New York： JMLR.org， 2017： 1480-1490.
58	CHEN R T Q， LI X C， GROSSE R， et al. Isolating sources of disentanglement in VAEs［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 2615-2625.
59	RIDGEWAY K， MOZER M C. Learning deep disentangled embeddings with the F-statistic loss［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 185-194.
60	KUMAR A， SATTIGERI P， BALAKRISHNAN A. Variational inference of disentangled latent concepts from unlabeled observations［EB/OL］. （2018-12-27）［2020-09-27］..
61	IIZUKA S， SIMO-SERRA E， ISHIKAWA H. Let there be color！： joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification［J］. ACM Transactions on Graphics， 2016， 35（4）： No.110. 10.1145/2897824.2925974
62	EIGEN D， FERGUS R. Predicting depth， surface normals and semantic labels with a common multi-scale convolutional architecture［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 2650-2658. 10.1109/iccv.2015.304
63	ISOLA P， ZHU J Y， ZHOU T H， et al. Image-to-image translation with conditional adversarial networks［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 5967-5976. 10.1109/cvpr.2017.632
64	ZHU J Y， PARK T， ISOLA P， et al. Unpaired image-to-image translation using cycle-consistent adversarial networks［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 2223-2232. 10.1109/iccv.2017.244
65	RONNEBERGER O， FISCHER P， BROX T. U-net： convolutional networks for biomedical image segmentation［C］// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS9351. Cham： Springer， 2015： 234-241.
66	MA L， SUN Q， GEORGOULIS S， et al. Disentangled person image generation［C］// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 99-108. 10.1109/cvpr.2018.00018
67	BARROW H G， TENENBAUM J M. Recovering intrinsic scene characteristics from images［M］// HANSON A， RISEMAN E， Computer Vision Systems. New York： Academic Press， 1978： 3-26.
68	Y， COURVILLE A， VINCENT P. Representation learning： a review and new perspectives［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2013， 35（8）： 1798-1828. 10.1109/tpami.2013.50
69	GONZALEZ-GARCIA A， WEIJER J V D， BENGIO Y. Image-to-image translation for cross-domain disentanglement［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 1294-1305.
70	ZHU J Y， ZHANG R， PATHAK D， et al. Toward multimodal image-to-image translation［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 465-476.
71	LEE H Y， TSENG H Y， MAO Q， et al. DRIT++： diverse image-to-image translation via disentangled representations［J］. International Journal of Computer Vision， 2020， 128（10/11）： 2402-2417. 10.1007/s11263-019-01284-z
72	白静，田栋文，张霖，等. 跨域变分对抗自编码器［J］. 计算机辅助设计与图形学学报， 2020， 32（9）：1402-1410. 10.3724/SP.J.1089.2020.18115
	BAI J， TIAN D W， ZHANG L， et al. Cross-domain variational adversarial autoencoder［J］. Journal of Computer-Aided Design and Graphics， 2020， 32（9）：1402-1410. 10.3724/SP.J.1089.2020.18115
73	CHIAPPA S， RACANIERE S， WIERSTRA D， et al. Recurrent environment simulators［EB/OL］. （2017-04-19）［2020-09-27］..
74	AGRAWAL P， NAIR A， ABBEEL P， et al. Learning to poke by poking： experiential learning of intuitive physics［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2016： 5092-5100. 10.1109/icra.2017.7989247
75	DENTON E， BIRODKAR V. Unsupervised learning of disentangled representations from video［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 4417-4426.
76	徐思. 基于对抗自编码器的半监督分类模型研究［D］. 青岛：青岛大学， 2019. 10.3934/mfc.2019002
	XU S. Research on semi-supervised classification model based on adversarial auto-encoder［D］. Qingdao： Qingdao University， 2019. 10.3934/mfc.2019002
77	SUN P F， SU X， GUO S Q， et al. Cycle representation-disentangling network： learning to completely disentangle spatial-temporal features in video［J］. Applied Intelligence， 2020， 50（12）： 4261-4280. 10.1007/s10489-020-01750-z
78	ZHU J Y， ZHANG Z T， ZHANG C K， et al. Visual object networks： image generation with disentangled 3D representations［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 118-129.
79	LOCATELLO F， BAUER S， LUCIC M， et al. Challenging common assumptions in the unsupervised learning of disentangled representations［C］// Proceedings of the 36th International Conference on Machine Learning. New York： JMLR.org， 2019： 4114-4124. 10.1609/aaai.v34i09.7120
80	LOCATELLO F， BAUER S， LUCIC M， et al. A sober look at the unsupervised learning of disentangled representations and their evaluation［J］. Journal of Machine Learning， 2020， 21： 1-62. 10.1609/aaai.v34i09.7120
81	STEENKISTE S VAN， LOCATELLO F， SCHMIDHUBER J， et al. Are disentangled representations helpful for abstract visual reasoning？［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2019： 14245-14258.
82	DO K， TRAN T. Theory and evaluation metrics for learning disentangled representations［EB/OL］. （2020-02-04）［2020-09-27］..

[1]	唐廷杰, 黄佳进, 秦进, 陆辉. 基于图共现增强多层感知机的会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2357-2364.
[2]	邓凯丽, 魏伟波, 潘振宽. 改进掩码自编码器的工业缺陷检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2595-2603.
[3]	杨莹, 郝晓燕, 于丹, 马垚, 陈永乐. 面向图神经网络模型提取攻击的图数据生成方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2483-2492.
[4]	姚梓豪, 栗远明, 马自强, 李扬, 魏良根. 基于机器学习的多目标缓存侧信道攻击检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1862-1871.
[5]	陈学斌, 任志强, 张宏扬. 联邦学习中的安全威胁与防御措施综述[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1663-1672.
[6]	李宗禹, 强思维, 郭晓波, 朱振峰. 重加权的对抗变分自编码器及其在工业因果效应估计中的应用[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1099-1106.
[7]	佘维, 李阳, 钟李红, 孔德锋, 田钊. 基于改进实数编码遗传算法的神经网络超参数优化[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 671-676.
[8]	郑毅, 廖存燚, 张天倩, 王骥, 刘守印. 面向城区的基于图去噪的小区级RSRP估计方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 855-862.
[9]	张卓, 陈花竹. 基于一致性和多样性的多尺度自表示学习的深度子空间聚类[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 353-359.
[10]	李博, 黄建强, 黄东强, 王晓英. 基于异构平台的稀疏矩阵向量乘自适应计算优化[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3867-3875.
[11]	陈学斌, 屈昌盛. 面向联邦学习的后门攻击与防御综述[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3459-3469.
[12]	蒋辉, 闫秋艳, 姜竹郡. 面向多元时间序列异常检测的对称正定自编码器方法[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3294-3299.
[13]	孙仁科, 皇甫志宇, 陈虎, 李仲年, 许新征. 神经架构搜索综述[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 2983-2994.
[14]	柴汶泽, 范菁, 孙书魁, 梁一鸣, 刘竟锋. 深度度量学习综述[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 2995-3010.
[15]	尹春勇, 周永成. 双端聚类的自动调整聚类联邦学习[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3011-3020.

解耦表征学习研究进展

Research advances in disentangled representation learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献 82

相关文章 15

编辑推荐

Metrics