浏览全部资源
扫码关注微信
Received：21 January 2022，
Revised：2022-05-16，
Published：16 April 2023
移动端阅览
表示学习是机器学习研究的核心问题之一。机器学习算法的输入表征从过去主流的手工特征过渡到现在面向多媒体数据的潜在表示，使算法性能获得了巨大提升。然而，视觉数据的表示通常是高度耦合的，即输入数据的所有信息成分被编码进同一个特征空间，从而互相影响且难以区分，使得表示的可解释性不高。解耦表示学习旨在学习一种低维的可解释性抽象表示，可以识别并分离出隐藏在高维观测数据中的不同潜在变化因素。通过解耦表示学习，可以捕获到单个变化因素信息并通过相对应的潜在子空间进行控制，因此解耦表示更具有可解释性。解耦表征可用于提高样本效率和对无关干扰因素的容忍度，为数据中的复杂变化提供一种鲁棒性表示，提取的语义信息对识别分类、域适应等人工智能下游任务具有重要意义。本文首先介绍并分析解耦表示的研究现状及其因果机制，总结解耦表示的3个重要性质。然后，将解耦表示学习算法分为4类，并从数学描述、类型特点及适用范围3个方面进行归纳及对比。随后，分类总结了现有解耦表示工作中常用的损失函数、数据集及客观评估指标。最后，总结了解耦表示学习在实际问题中的各类应用，并对其未来发展进行了探讨。
Representation learning is essential for machine learning technique nowadays. The transition of input representations have been developing intensively in algorithm performance benefited from the growth of hand-crafted features to the representation for multi-media data. However， the representations of visual data are often highly entangled. The interpretation challenges are to be faced because all information components are encoded into the same feature space. Disentangled representation learning （DRL） aims to learn a low-dimensional interpretable abstract representation that can sort the multiple factors of variation out in high-dimensional observations. In the disentangled representation， we can capture and manipulate the information of a single factor of variation through the corresponding latent subspace， which makes it more interpretable. DRL can improve sample efficiency and tolerance to the nuisance variables and offer robust representation of complex variations. Their semantic information is extracted and beneficial for artificial intelligence （AI） downstream tasks like recognition， classification and domain adaptation. Our summary is focused on brief introduction to the definition， research development and applications of DRL. Some of independent component analysis （ICA）-nonlinear DRL researches are covered as well since the DRL is similar to the identifiability issue of nonlinear independent component analysis （nonlinear ICA）. The cause and effects mechanism of DRL as high-dimensional ground truth data is generated by a set of unobserved changing factors （generating factors）. The DRL can be used to model the factors of variation in terms of latent representation， and the observed data generation process is restored. We summarize the key elements that a well-defined disentangled representation should be qualified into three aspects， which are 1） modularity， 2） compactness， and 3） explicitness. First， explicitness consists of the two sub-requirements of completeness and informativeness. Then， current DRL types are categorized into 1） dimension-wise disentanglement， 2） semantic-based disentanglement， 3） hierarchical disentanglement， and 4） nonlinear ICA four types in terms of its formulation， characteristics， and scope of application. Dimension-wise disentanglement is assumed that the generative factors are solely and each dimension of latent vector can be separated and mapped， which is suitable for learning the disentangled representation of simple synthetic visual data. Semantic-based disentanglement is hypnotized that some semantic information is solely as well. The generative factors are group-disentangled in terms of specific semantics and they are mapped to different latent spaces， which is suitable for complicated ground truth data. Hierarchical disentanglement is based on the assumption that there is a correlation between generative factors at different levels of abstraction. The generative factors are disentangled by group from the bottom up and they can be mapped to latent space of different semantic abstraction levels to form a hierarchical disentangled representation. Nonlinear ICA provides an identifiable method for observed data-mixed disentangling unknown generative factors through a nonlinear reversible generator. For the motivation of loss functions， the loss functions can be commonly used in disentangled representation learning， which are grouped into three categories： 1） modularity constraint： a single latent variable-constrained in the disentangled representation to capture only a single or a single group of factors of variation， and it promotes the separation of factors of variation mutually； 2） explicitness constraint： current latent variable of the latent representation is activated to encode the ground truth of the corresponding generating factor effectively， and the entire latent representation contains complete information about all generative factors； and 3） multi-purpose constraint： loss-related can optimize multiple disentangled representation， including modularity， compactness， and explicitness of the disentangled representation at the same time. The model-relevant can combine multiple loss constraint terms to form the final hybrid objective function. We compare the scope of application and limitations of each type of loss functions and summarize the classical disentangled representation works using the hybrid objective function further.
Achille A ， Eccles T ， Matthey L ， Burgess C ， Watters N ， Lerchner A and Higgins I . 2018 . Life-long disentangled representation learning with cross-domain latent homologies // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc
Aifanti N ， Papachristou C and Delopoulos A . 2010 . The MUG facial expression database // Proceedings of the 11th International Workshop on Image Analysis for Multimedia Interactive Services WIAMIS 10 . Desenzano del Garda， Italy ： IEEE： 1 - 4
Aubry M ， Maturana D ， Efros A A ， Russell B C and Sivic J . 2014 . Seeing 3D chairs： exemplar part-based 2D-3D alignment using a large dataset of CAD models // Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus， USA ： IEEE： 3762 - 3769 ［ DOI： 10.1109/CVPR.2014.487 http://dx.doi.org/10.1109/CVPR.2014.487 ］
Bai J W ， Kong S F and Gomes C . 2020a . Disentangled variational autoencoder based multi-label classification with covariance-aware multivariate probit model // Proceedings of the 29th International Joint Conference on Artificial Intelligence . Yokohama， Japan ： IJCAI.org： 4313 - 4321 ［ DOI： 10.24963/ijcai.2020/595 http://dx.doi.org/10.24963/ijcai.2020/595 ］
Bai Y ， Lou Y H ， Dai Y X ， Liu J ， Chen Z Q and Duan L Y . 2020b . Disentangled feature learning network for vehicle re-identification // Proceedings of the 29th International Joint Conference on Artificial Intelligence . Yokohama， Japan ： IJCAI.org： 474 - 480 ［ DOI： 10.24963/ijcai.2020/66 http://dx.doi.org/10.24963/ijcai.2020/66 ］
Baktashmotlagh M ， Faraki M ， Drummond T and Salzmann M . 2018 . Learning factorized representations for open-set domain adaptation . ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1805.12277.pdf https://arxiv.org/pdf/1805.12277.pdf
Bass C ， da Silva M ， Sudre C ， Tudosiu P D ， Smith S M and Robinson E C . 2020 . ICAM： interpretable classification via disentangled representations and feature attribution mapping // Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates Inc.： 7697 - 7709
Bengio Y ， Courville A and Vincent P . 2013 . Representation learning： a review and new perspectives . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 35 （ 8 ）： 1798 - 1828 ［ DOI： 10.1109/TPAMI.2013.50 http://dx.doi.org/10.1109/TPAMI.2013.50 ］
Bepler T ， Zhong E D ， Kelley K ， Brignole E and Berger B . 2019 . Explicitly disentangling image content from translation and rotation with spatial-VAE // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Curran Associates， Inc. ： 15435 - 15445
Bi S ， Sunkavalli K ， Perazzi F ， Shechtman E ， Kim V G and Ramamoorthi R . 2019 . Deep CG2Real： synthetic-to-real translation via image disentanglement // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 2730 - 2739 ［ DOI： 10.1109/ICCV.2019.00282 http://dx.doi.org/10.1109/ICCV.2019.00282 ］
Blank M ， Gorelick L ， Shechtman E ， Irani M and Basri R . 2005 . Actions as space-time shapes // Proceedings of the 10th IEEE International Conference on Computer Vision . Beijing， China ： IEEE： 1395 - 1402 ［ DOI： 10.1109/ICCV.2005.28 http://dx.doi.org/10.1109/ICCV.2005.28 ］
Bouchacourt D ， Tomioka R and Nowozin S . 2018 . Multi-level variational autoencoder： learning disentangled representations from grouped observations . Proceedings of 2018 AAAI Conference on Artificial Intelligence ， 32 （ 1 ）： 2095 - 2102 ［ DOI： 10.1609/aaai.v32i1.11867 http://dx.doi.org/10.1609/aaai.v32i1.11867 ］
Bromley J ， Guyon I ， LeCun Y ， Säckinger E and Shah R . 1993 . Signature verification using a “Siamese” time delay neural network // Proceedings of the 6th International Conference on Neural Information Processing Systems . Denver， Colorado， USA ： Morgan Kaufmann Publishers Inc.： 737 - 744
Burgess C and Kim H . 2018 . 3 D shapes dataset ［EB/OL］. ［ 2022-01-21 ］. https://github.com/deepmind/3d-shapes https://github.com/deepmind/3d-shapes
Burgess C P ， Higgins I ， Pal A ， Matthey L ， Watters N ， Desjardins G and Lerchner A . 2018 . Understanding disentangling in β -VAE ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1804.03599.pdf https://arxiv.org/pdf/1804.03599.pdf
Cai R C ， Li Z J ， Wei P F ， Qiao J ， Zhang K and Hao Z F . 2019 . Learning disentangled semantic representation for domain adaptation // Proceedings of the 28th International Joint Conference on Artificial Intelligence . Macao， China ： IJCAI.org： 2060 - 2066 ［ DOI： 10.24963/ijcai.2019/285 http://dx.doi.org/10.24963/ijcai.2019/285 ］
Carbonneau M A ， Zaïdi J ， Boilard J and Gagnon G . 2022 . Measuring disentanglement： a review of metrics . IEEE Transactions on Neural Networks and Learning Systems . 2022 ： 1 - 15 ［ DOI： 10.1109/TNNLS.2022.3218982 http://dx.doi.org/10.1109/TNNLS.2022.3218982 ］
Chang M B ， Ullman T ， Torralba A and Tenenbaum J B . 2017 . A compositional object-based approach to learning physical dynamics ［EB/OL］. ［ 2022-01-21 ］. http：//arxiv.org/pdf/1612.00341.pdf http://arxiv.org/pdf/1612.00341.pdf
Chartsias A ， Joyce T ， Papanastasiou G ， Semple S ， Williams M ， Newby D E ， Dharmakumar R and Tsaftaris S A . 2019 . Disentangled representation learning in cardiac image analysis . Medical Image Analysis ， 58 ： # 101535 ［ DOI： 10.1016/j.media.2019.101535 http://dx.doi.org/10.1016/j.media.2019.101535 ］
Chartsias A ， Papanastasiou G ， Wang C J ， Stirrat C ， Semple S ， Newby D ， Dharmakumar R and Tsaftaris S A . 2020 . Multimodal cardiac segmentation using disentangled representation learning // Proceedings of the 10th International Workshop on Statistical Atlases and Computational Models of the Heart . Multi-Sequence CMR Segmentation， CRT-EPiggy and LV Full Quantification Challenges. Shenzhen， China ： Springer： 128 - 137 ［ DOI： 10.1007/978-3-030-39074-7_14 http://dx.doi.org/10.1007/978-3-030-39074-7_14 ］
Chen H Y ， Chen F and He H J . 2021a . SSC-GAN： a novel gan based on the same solution constraints of first-order ODEs . International Journal of Pattern Recognition and Artificial Intelligence . 35 （ 11 ）： # 2152018 ［ DOI： 10.1142/S0218001421530062 http://dx.doi.org/10.1142/S0218001421530062 ］
Chen H ， Lagadec B and Bremond F . 2021b . ICE： inter-instance contrastive encoding for unsupervised person re-identification // Proceedings of 2021 IEEE International Conference on Computer Vision . IEEE ： 14960 - 14969
Chen R T Q ， Li X C ， Grosse R and Duvenaud D . 2019 . Isolating sources of disentanglement in variational autoencoders ［EB/OL］.［ 2022-01-21 ］. https://arxiv.org/pdf/1802.04942.pdf https://arxiv.org/pdf/1802.04942.pdf
Chen X ， Duan Y ， Houthooft R ， Schulman J ， Sutskever I and Abbeel P . 2016 . InfoGAN： interpretable representation learning by information maximizing generative adversarial nets // Proceedings of the 30th International Conference on Neural Information Processing Systems . Barcelona， Spain ： Curran Associates Inc.： 2180 - 2188
Chen X ， Lian C F ， Wang L ， Deng H N ， Kuang T S ， Fung S H ， Gateno J ， Shen D G ， Xia J J and Yap P T . 2021c . Diverse data augmentation for learning image segmentation with cross-modality annotations // Medical Image Analysis . 71 ： # 102060 ［DOI： 10.1016/j.media.2021.102060］
Choi Y J ， Choi M J ， Kim M Y ， Ha J W ， Kim S H and Choo J . 2018 . StarGAN： unified generative adversarial networks for multi-domain image-to-image translation // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 8789 - 8797
Cohen G ， Afshar S ， Tapson J and van Schaik A . 2017 . EMNIST： an extension of MNIST to handwritten letters // Proceedings of 2017 International Joint Conference on Neural Networks （IJCNN） . Anchorage， USA ： IEEE： 2921 - 2926 ［ DOI： 10.1109/IJCNN.2017.7966217 http://dx.doi.org/10.1109/IJCNN.2017.7966217 ］
Creager E ， Madras D ， Jacobsen J H ， Weis M A ， Swersky K ， Pitassi T and Zemel R . 2019 . Flexibly fair representation learning by disentanglement // Proceedings of the 36th International Conference on Machine Learning . Long Beach， USA ： PMLR： 1436 - 1445
Deng Y ， Yang J L ， Chen D ， Wen F and Tong X . 2020 . Disentangled and controllable face image generation via 3D imitative-contrastive learning // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 5153 - 5162 ［ DOI： 10.1109/CVPR42600.2020.00520 http://dx.doi.org/10.1109/CVPR42600.2020.00520 ］
Denton E and Birodkar V . 2017 . Unsupervised learning of disentangled representations from video // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， USA ： Curran Associates Inc.： 4417 - 4426
Detlefsen N S and Hauberg S . 2019 . Explicit disentanglement of appearance and perspective in generative models // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Curran Associates， Inc. ： 1018 - 1028
Ding W ， Li L ， Huang L and Zhuang X . 2022 . Unsupervised multi-modality registration network based on spatially encoded gradient information // Statistical Atlases and Computational Models of the Heart . Multi-Disease， Multi-View， and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge. Strasbourg， France ： Cham： Springer International Publishing： 151 - 159 ［ DOI： 10.1007/978-3-030-93722-5_17 http://dx.doi.org/10.1007/978-3-030-93722-5_17 ］
Ding Z ， Xu Y F ， Xu W J ， Parmar G ， Yang Y ， Welling M and Tu Z W . 2020 . Guided variational autoencoder for disentanglement learning // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Seattle， USA ： IEEE： 7917 - 7926 ［ DOI： 10.1109/CVPR42600.2020.00794 http://dx.doi.org/10.1109/CVPR42600.2020.00794 ］
Dinh L ， Sohl-Dickstein J and Bengio S . 2017 . Density estimation using real NVP ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1605.08803.pdf https://arxiv.org/pdf/1605.08803.pdf
Dou Q ， Ouyang C ， Chen C ， Chen H ， Glocker B ， Zhuang X H and Heng P A . 2019 . PnP-AdaNet： plug-and-play adversarial domain adaptation network at unpaired cross-modality cardiac segmentation . IEEE Access . 7 ： 99065 - 99076 ［ DOI： 10.1109/ACCESS.2019.2929258 http://dx.doi.org/10.1109/ACCESS.2019.2929258 ］
Duan B Y ， Fu C Y ， Li Y ， Song X G and He R . 2020 . Cross-spectral face hallucination via disentangling independent factors // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 7927 - 7935 ［ DOI： 10.1109/CVPR42600.2020.00795 http://dx.doi.org/10.1109/CVPR42600.2020.00795 ］
Dupont E . 2018 . Learning disentangled joint continuous and discrete representations // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc.： 708 - 718
Dutta A and Akata Z . 2019 . Semantically tied paired cycle consistency for zero-shot sketch-based image retrieval // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 5089 - 5098
Dutta T ， Singh A and Biswas S . 2021 . StyleGuide： zero-shot sketch-based image retrieval using style-guided image generation . IEEE Transactions on Multimedia . 23 ： 2833 - 2842 ［ DOI： 10.1109/TMM.2020.3017918 http://dx.doi.org/10.1109/TMM.2020.3017918 ］
Eastwood C and Williams C K I . 2018 . A framework for the quantitative evaluation of disentangled representations // Proceedings of the 6th International Conference on Learning Representations . Vancouver， Canada ： OpenReview.net
Eitz M ， Richter R ， Boubekeur T and Hildebrand K . 2012 . Sketch-based shape retrieval . ACM Transactions on graphics （TOG） . 31 （ 4 ）： 1 - 10 ［ DOI： 10.1145/2185520.2185527 http://dx.doi.org/10.1145/2185520.2185527 ］
Eom C and Ham B . 2019 . Learning disentangled representation for robust person re-identification // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Curran Associates， Inc. ： 5297 - 5308
Esmaeili B ， Wu H ， Jain S ， Bozkurt A ， Siddharth N ， Paige B ， Brooks D H ， Dy J and Van de Meent J W . 2019 . Structured disentangled representations // Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics . Naha， Japan ： PMLR： 2525 - 2534
Estermann B ， Marks M and Yanik M F . 2020 . Robust disentanglement of a few factors at a time using rPU-VAE // Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates Inc.： 13387 - 13398
Fidler S ， Dickinson S and Urtasun R . 2012 . 3D object detection and viewpoint estimation with a deformable 3D cuboid model // Proceedings of the 25th International Conference on Neural Information Processing Systems . Lake Tahoe， USA ： Curran Associates Inc.： 611 - 619
Fraccaro M ， Kamronn S ， Paquet U and Winther O . 2017 . A disentangled recognition and nonlinear dynamics model for unsupervised learning // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， USA ： Curran Associates Inc.： 3604 - 3613
Fu Y ， Wei Y ， Zhou Y ， Shi H ， Huang G ， Wang X ， Yao Z and Huang T . 2019 . Horizontal pyramid matching for person re-identification . Proceedings of 2019 AAAI Conference on Artificial Intelligence ， 33 （ 1 ）， 8295 - 8302 ［ DOI： 10.1609/aaai.v33i01.33018295 http://dx.doi.org/10.1609/aaai.v33i01.33018295 ］
Gilbert A ， Collomosse J ， Jin H L and Price B . 2018 . Disentangling structure and aesthetics for style-aware image completion // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 1848 - 1856 ［ DOI： 10.1109/CVPR.2018.00198 http://dx.doi.org/10.1109/CVPR.2018.00198 ］
Gondal M W ， Wüthrich M ， Miladinović Đ ， Locatello F ， Breidt M ， Volchkov V ， Akpo J ， Bachem O ， Schölkopf B and Bauer S . 2019 . On the transfer of inductive bias from simulation to the real world： a new disentanglement dataset // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates， Inc.： 15740 - 15751
Gonzalez-Garcia A ， Van de Weijer J and Bengio Y . 2018 . Image-to-image translation for cross-domain disentanglement // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc.： 1294 - 1305
Goodfellow I J ， Pouget-Abadie J ， Mirza M ， Xu B ， Warde-Farley D ， Ozair S ， Courville A and Bengio Y . 2014 . Generative adversarial nets // Proceedings of the 27th International Conference on Neural Information Processing Systems . Montreal， Canada ： MIT Press： 2672 - 2680
Gowal S ， Qin C L ， Huang P S ， Cemgil T ， Dvijotham K ， Mann T and Kohli P . 2020 . Achieving robustness in the wild via adversarial mixing with disentangled representations // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 1208 - 1217 ［ DOI： 10.1109/CVPR42600.2020.00129 http://dx.doi.org/10.1109/CVPR42600.2020.00129 ］
Grathwohl W and Wilson A . 2016 . Disentangling space and time in video with hierarchical variational auto-encoders ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1612.04440.pdf https://arxiv.org/pdf/1612.04440.pdf
Gulrajani I ， Kumar K ， Ahmed F ， Taïga A A ， Visin F ， Vzquez D and Courville A C . 2016 . PixelVAE： a latent variable model for natural images . ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1611.05013.pdf https://arxiv.org/pdf/1611.05013.pdf
Guo W K ， Huang H B ， Kong X W and He R . 2019 . Learning disentangled representation for cross-modal retrieval with deep mutual information estimation // Proceedings of the 27th ACM International Conference on Multimedia . Nice， France ： ACM： 1712 - 1720 ［ DOI： 10.1145/3343031.3351053 http://dx.doi.org/10.1145/3343031.3351053 ］
Hadad N ， Wolf L and Shahar M . 2018 . A two-step disentanglement method // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 772 - 780 ［ DOI： 10.1109/CVPR.2018.00087 http://dx.doi.org/10.1109/CVPR.2018.00087 ］
Hamaguchi R ， Sakurada K and Nakamura R . 2019 . Rare event detection using disentangled representation learning // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 9319 - 9327 ［ DOI： 10.1109/CVPR.2019.00955 http://dx.doi.org/10.1109/CVPR.2019.00955 ］
Higgins I ， Amos D ， Pfau D ， Racaniere S ， Matthey L ， Rezende D and Lerchner A . 2018 . Towards a definition of disentangled representations ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1812.02230.pdf https://arxiv.org/pdf/1812.02230.pdf
Higgins I ， Matthey L ， Pal A ， Burgess C ， Glorot X ， Botvinick M ， Mohamed S and Lerchner A . 2017 . β -VAE： learning basic visual concepts with a constrained variational framework // Proceedings of the 5th International Conference on Learning Representations . Toulon， France ： OpenReview. net
Hinton G E and Salakhutdinov R R . 2006 . Reducing the dimensionality of data with neural networks . Science ， 313 （ 5786 ）： 504 - 507 ［ DOI： 10.1126/science.1127647 http://dx.doi.org/10.1126/science.1127647 ］
Hochreiter S and Schmidhuber J . 1997 . Long short-term memory . Neural Computation ， 9 （ 8 ）： 1735 - 1780 ［ DOI： 10.1162/neco.1997.9.8.1735 http://dx.doi.org/10.1162/neco.1997.9.8.1735 ］
Hsieh J T ， Liu B B ， Huang D A ， Li F F and Niebles J C . 2018 . Learning to decompose and disentangle representations for video prediction // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc.： 515 - 524
Hsu W N ， Zhang Y and Glass J . 2017 . Unsupervised learning of disentangled and interpretable representations from sequential data // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， USA ： Curran Associates Inc.： 1876 - 1887
Huang X ， Liu M Y ， Belongie S and Kautz J . 2018 . Multimodal unsupervised image-to-image translation // Proceedings of the 15th European Conference on Computer Vision （ECCV） . Munich， Germany ： Springer： 172 - 189
Hwang H ， Kim G H ， Hong S and Kim K E . 2020 . Variational interaction information maximization for cross-domain disentanglement // Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates Inc.： 22479 - 22491
Jiang Z H ， Wu Q Y ， Chen K Y and Zhang J Y . 2019 . Disentangled representation learning for 3D face shape // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 11949 - 11958 ［ DOI： 10.1109/CVPR.2019.01223 http://dx.doi.org/10.1109/CVPR.2019.01223 ］
Jung D ， Lee J ， Yi J H and Yoon S . 2020 . ICAPS： an interpretable classifier via disentangled capsule networks // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 314 - 330 ［ DOI： 10.1007/978-3-030-58529-7_19 http://dx.doi.org/10.1007/978-3-030-58529-7_19 ］
Kim H and Mnih A . 2018 . Disentangling by factorising // Proceedings of the 35th International Conference on Machine Learning . Stockholm， Sweden ： PMLR： 2649 - 2658
Khemakhem I ， Kingma D ， Monti R and Hyvarinen A . 2020 . Variational autoencoders and nonlinear ICA： a unifying framework // Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics . Palermo， Italy ： PMLR： 2207 - 2217
Kingma D P and Welling M . 2013 . Auto-encoding variational Bayes ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1312.6114v1.pdf https://arxiv.org/pdf/1312.6114v1.pdf
Klindt D ， Schott L ， Sharma Y ， Ustyuzhaninov I ， Brendel W ， Bethge M and Paiton D . 2021 . Towards nonlinear disentanglement in natural data with temporal sparse coding . ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/2007.10930.pdf https://arxiv.org/pdf/2007.10930.pdf
Kondo R ， Kawano K ， Koide S and Kutsuna T . 2019 . Flow-based image-to-image translation with feature disentanglement // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates， Inc.： 4168 - 4178
Kotovenko D ， Sanakoyeu A ， Lang S and Ommer B . 2019 . Content and style disentanglement for artistic style transfer // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 4421 - 4430 ［ DOI： 10.1109/ICCV.2019.00452 http://dx.doi.org/10.1109/ICCV.2019.00452 ］
Krause J ， Stark M ， Deng J and Li F F . 2013 . 3D object representations for fine-grained categorization // Proceedings of 2013 IEEE International Conference on Computer Vision （ICCV） Workshops . Sydney， Australia ： IEEE： 554 - 561
Kulkarni T D ， Whitney W F ， Kohli P and Tenenbaum J B . 2015 . Deep convolutional inverse graphics network // Proceedings of the 28th International Conference on Neural Information Processing Systems . Montreal， Canada ： MIT Press： 2539 - 2547
Kumar A ， Sattigeri P and Balakrishnan A . 2018 . Variational inference of disentangled latent concepts from unlabeled observations ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1711.00848.pdf https://arxiv.org/pdf/1711.00848.pdf
Lai C S ， You Z Z ， Huang C C ， Tsai Y H and Chiu W C . 2020 . Colorization of depth map via disentanglement // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 450 - 466 ［ DOI： 10.1007/978-3-030-58571-6_27 http://dx.doi.org/10.1007/978-3-030-58571-6_27 ］
LeCun Y ， Bottou L ， Bengio Y and Haffner P . 1998 . Gradient-based learning applied to document recognition . Proceedings of the IEEE ， 86 （ 11 ）： 2278 - 2324 ［ DOI： 10.1109/5.726791 http://dx.doi.org/10.1109/5.726791 ］
LeCun Y ， Huang F J and Bottou L . 2004 . Learning methods for generic object recognition with invariance to pose and lighting // Proceedings of 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Washington， USA ： IEEE： 97 - 104 ［ DOI： 10.1109/CVPR.2004.144 http://dx.doi.org/10.1109/CVPR.2004.144 ］
Lee H Y ， Tseng H Y ， Huang J B ， Singh M and Yang M H . 2018 . Diverse image-to-image translation via disentangled representations // Proceedings of the 15th European Conference on Computer Vision （ECCV） . Munich， Germany ： Springer： 36 - 52 ［ DOI： 10.1007/978-3-030-01246-5_3 http://dx.doi.org/10.1007/978-3-030-01246-5_3 ］
Lee W ， Kim D ， Hong S and Lee H . 2020 . High-fidelity synthesis with disentangled representation // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 157 - 174 ［ DOI： 10.1007/978-3-030-58574-7_10 http://dx.doi.org/10.1007/978-3-030-58574-7_10 ］
Li P P ， Huang H B ， Hu Y B ， Wu X ， He R and Sun Z N . 2020a . Hierarchical face aging through disentangled latent characteristics // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 86 - 101 ［ DOI： 10.1007/978-3-030-58580-8_6 http://dx.doi.org/10.1007/978-3-030-58580-8_6 ］
Li P P ， Liu Y L ， Shi H L ， Wu X ， Hu Y B ， He R and Sun Z N . 2020b . Dual-structure disentangling variational generation for data-limited face parsing // Proceedings of the 28th ACM International Conference on Multimedia . Seattle， USA ： ACM： 556 - 564 ［ DOI： 10.1145/3394171.3413919 http://dx.doi.org/10.1145/3394171.3413919 ］
Li S ， Hooi B and Lee G H . 2020c . Identifying through flows for recovering latent representations ［EB/OL］.［ 2022-01-21 ］. https://arxiv.org/pdf/1909.12555.pdf https://arxiv.org/pdf/1909.12555.pdf
Li W ， Zhao R ， Xiao T and Wang X . 2014 . DeepReID： deep filter pairing neural network for person re-identification // Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus， USA ： IEEE： 152 - 159
Li X ， Jin X ， Lin J X ， Liu S ， Wu Y J ， Yu T ， Zhou W and Chen Z B . 2020d . Learning disentangled feature representation for hybrid-distorted image restoration // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 313 - 329 ［ DOI： 10.1007/978-3-030-58526-6_19 http://dx.doi.org/10.1007/978-3-030-58526-6_19 ］
Li X ， Makihara Y ， Xu C ， Yagi Y and Ren M W . 2020e . Gait recognition via semi-supervised disentangled representation learning to identity and covariate features // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 13306 - 13316 ［ DOI： 10.1109/CVPR42600.2020.01332 http://dx.doi.org/10.1109/CVPR42600.2020.01332 ］
Li Y H ， Singh K K ， Ojha U and Lee Y J . 2020f . MixNMatch： multifactor disentanglement and encoding for conditional image generation // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 8036 - 8045 ［ DOI： 10.1109/CVPR42600.2020.00806 http://dx.doi.org/10.1109/CVPR42600.2020.00806 ］
Li Y Z and Mandt S . 2018 . Disentangled sequential autoencoder // Proceedings of the 35th International Conference on Machine Learning . Stockholm， Sweden ： PMLR： 5670 - 5679
Li Z Y ， Murkute J V ， Gyawali P K and Wang L W . 2020g . Progressive learning and disentanglement of hierarchical representations ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/2002.10549.pdf https://arxiv.org/pdf/2002.10549.pdf
Liao L ， Hu R M ， Xiao J and Wang Z Y . 2019 . Artist-Net： decorating the inferred content with unified style for image inpainting . IEEE Access ， 7 ： 36921 - 36933 ［ DOI： 10.1109/ACCESS.2019.2905268 http://dx.doi.org/10.1109/ACCESS.2019.2905268 ］
Liu A H ， Liu Y C ， Yeh Y Y and Wang Y C F . 2018a . A unified feature disentangler for multi-domain image translation and manipulation // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc.： 2595 - 2604
Liu F ， Zhu R H ， Zeng D ， Zhao Q J and Liu X M . 2018b . Disentangling features in 3D face shapes for joint face reconstruction and recognition // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 5216 - 5225 ［ DOI： 10.1109/CVPR.2018.00547 http://dx.doi.org/10.1109/CVPR.2018.00547 ］
Liu Y ， Wang Z W ， Jin H L and Wassell I . 2018c . Multi-task adversarial network for disentangled feature learning // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 3743 - 3751 ［ DOI： 10.1109/CVPR.2018.00394 http://dx.doi.org/10.1109/CVPR.2018.00394 ］
Liu Y ， Wei F Y ， Shao J ， Sheng L ， Yan J J and Wang X G . 2018e . Exploring disentangled feature representation beyond face identification // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 2080 - 2089 ［ DOI： 10.1109/CVPR.2018.00222 http://dx.doi.org/10.1109/CVPR.2018.00222 ］
Liu Y C ， Yeh Y Y ， Fu T C ， Wang S D ， Chiu W C and Wang Y C F . 2018d . Detach and adapt： learning cross-domain disentangled deep representation // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 8867 - 8876 ［ DOI： 10.1109/CVPR.2018.00924 http://dx.doi.org/10.1109/CVPR.2018.00924 ］
Liu Z W ， Luo P ， Wang X G and Tang X O . 2015 . Deep learning face attributes in the wild // Proceedings of 2015 IEEE International Conference on Computer Vision （ICCV） . Santiago， Chile ： IEEE： 3730 - 3738 ［ DOI： 10.1109/ICCV.2015.425 http://dx.doi.org/10.1109/ICCV.2015.425 ］
Liu Z Y ， Zhang H W ， Chen Z H ， Wang Z Y and Ouyang W L . 2020 . Disentangling and unifying graph convolutions for skeleton-based action recognition // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 140 - 149 ［ DOI： 10.1109/CVPR42600.2020.00022 http://dx.doi.org/10.1109/CVPR42600.2020.00022 ］
Locatello F ， Abbati G ， Rainforth T ， Bauer S ， Schölkopf B and Bachem O . 2019a . On the fairness of disentangled representations // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates， Inc.： 14611 - 14624
Locatello F ， Bauer S ， Lucic M ， Raetsch G ， Gelly S ， Schölkopf B and Bachem O . 2019b . Challenging common assumptions in the unsupervised learning of disentangled representations // Proceedings of the 36th International Conference on Machine Learning . Long Beach， USA ： Curran Associates， Inc.： 7247 - 7283
Lorenz D ， Bereska L ， Milbich T and Ommer B . 2019 . Unsupervised part-based disentangling of object shape and appearance // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 10947 - 10956 ［ DOI： 10.1109/CVPR.2019.01121 http://dx.doi.org/10.1109/CVPR.2019.01121 ］
Lu B Y ， Chen J C and Chellappa R . 2019 . Unsupervised domain-specific deblurring via disentangled representations // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 10217 - 10226 ［ DOI： 10.1109/CVPR.2019.01047 http://dx.doi.org/10.1109/CVPR.2019.01047 ］
Ma J X ， Zhou C ， Cui P ， Yang H X and Zhu W W . 2019 . Learning disentangled representations for recommendation // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver Canada ： Curran Associates， Inc.： 5711 - 5722
Ma L Q ， Sun Q R ， Georgoulis S ， Van Gool L ， Schiele B and Fritz M . 2018 . Disentangled person image generation // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 99 - 108 ［ DOI： 10.1109/CVPR.2018.00018 http://dx.doi.org/10.1109/CVPR.2018.00018 ］
Massagué A C ， Zhang C ， Feric Z ， Camps O and Yu R . 2020 . Learning disentangled representations of video with missing data // Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates Inc.： 3625 - 3635
Matthey L ， Higgins I ， Hassabis D and Lerchner A . 2017 . dSprites： disentanglement testing sprites dataset ［EB/OL］. ［ 2022-01-21 ］. https://github.com/deepmind/dsprites-dataset/ https://github.com/deepmind/dsprites-dataset/
Miyato T ， Kataoka T ， Koyama M and Yoshida Y . 2018 . Spectral normalization for generative adversarial networks // Proceedings of the 35th International Conference on Machine Learning . Stockholm， Sweden ： PMLR
Netzer Y ， Wang T ， Coates A ， Bissacco A ， Wu B and Ng A Y . 2011 . Reading digits in natural images with unsupervised feature learning // NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011
Nie Q ， Liu Z W and Liu Y H . 2020a . Unsupervised 3D human pose representation with viewpoint and pose disentanglement // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 102 - 118 ［ DOI： 10.1007/978-3-030-58529-7_7 http://dx.doi.org/10.1007/978-3-030-58529-7_7 ］
Nie W L ， Karras T ， Garg A ， Debnath S ， Patney A ， Patel A B and Anandkumar A . 2020b . Semi-supervised StyleGAN for disentanglement learning // Proceedings of the 37th International Conference on Machine Learning . Virtual ： JMLR.org： 7360 - 7369
Niu X S ， Yu Z T ， Han H ， Li X B ， Shan S G and Zhao G Y . 2020 . Video-based remote physiological measurement via cross-verified feature disentangling // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 295 - 310 ［ DOI： 10.1007/978-3-030-58536-5_18 http://dx.doi.org/10.1007/978-3-030-58536-5_18 ］
Ojha U ， Singh K K ， Hsieh C J and Lee Y J . 2020 . Elastic-InfoGAN： unsupervised disentangled representation learning in class-imbalanced data // Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates Inc.： 18063 - 18075
Ouyang C ， Biffi C ， Chen C ， Kart T ， Qiu H Q and Rueckert D . 2022 . Self-supervised learning for few-shot medical image segmentation . IEEE Transactions on Medical Imaging . 41 （ 7 ）： 1837 - 1848 ［ DOI： 10.1109/TMI.2022.3150682 http://dx.doi.org/10.1109/TMI.2022.3150682 ］
Painter M ， Hare J and Prugel-Bennett A . 2020 . Linear disentangled representations and unsupervised action estimation // Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates Inc.： 13297 - 13307
Paysan P ， Knothe R ， Amberg B ， Romdhani S and Vetter T . 2009 . A 3 D face model for pose and illumination invariant face recognition// Proceedings of the 6th IEEE International Conference on Advanced Video and Signal based Surveillance . Genova， Italy： IEEE： 296 - 301 ［ DOI： 10.1109/AVSS.2009.58 http://dx.doi.org/10.1109/AVSS.2009.58 ］
Peebles W ， Peebles J ， Zhu J Y ， Efros A and Torralba A . 2020 . The hessian penalty： a weak prior for unsupervised disentanglement // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 581 - 597 ［ DOI： 10.1007/978-3-030-58539-6_35 http://dx.doi.org/10.1007/978-3-030-58539-6_35 ］
Pei C H ， Wu F P ， Huang L Q and Zhuang X H . 2021 . Disentangle domain features for cross-modality cardiac image segmentation // Medical Image Analysis . 71 ： # 102078 ［DOI： 10.1016/j.media.2021.102078］
Peng X ， Yu X ， Sohn K ， Metaxas D N and Chandraker M . 2017 . Reconstruction-based disentanglement for pose-invariant face recognition // Proceedings of 2017 IEEE International Conference on Computer Vision . Venice， Italy ： IEEE： 1632 - 1641 ［ DOI： 10.1109/ICCV.2017.180 http://dx.doi.org/10.1109/ICCV.2017.180 ］
Peng X C ， Huang Z J ， Sun X M and Saenko K . 2019 . Domain agnostic learning with disentangled representations // Proceedings of the 36th International Conference on Machine Learning . Long Beach， USA ： PMLR： 5102 - 5112
Pu N ， Chen W ， Liu Y ， Bakker E M and Lew M S . 2020 . Dual Gaussian-based variational subspace disentanglement for visible-infrared person re-identification // Proceedings of the 28th ACM International Conference on Multimedia . Seattle， USA ： ACM： 2149 - 2158 ［ DOI： 10.1145/3394171.3413673 http://dx.doi.org/10.1145/3394171.3413673 ］
Reed S ， Sohn K ， Zhang Y T and Lee H . 2014 . Learning to disentangle factors of variation with manifold interaction // Proceedings of the 31st International Conference on Machine Learning . Beijing， China ： JMLR.org： 1431 - 1439
Rezende D J ， Mohamed S and Wierstra D . 2014 . Stochastic backpropagation and approximate inference in deep generative models // Proceedings of the 31st International Conference on Machine Learning . Beijing， China ： JMLR.org： 1278 - 1286
Rezende D J and Mohamed S . 2015 . Variational inference with normalizing flows // Proceedings of the 32nd International Conference on Machine Learning . Lille， France ： JMLR.org： 1530 - 1538
Ridgeway K and Mozer M C . 2018 . Learning deep disentangled embeddings with the f-statistic loss // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc.： 185 - 194
Roberson P L ， McLaughlin P W ， Narayana V ， Troyer S ， Hixson G V and Kessler M L . 2005 . Use and uncertainties of mutual information for computed tomography/magnetic resonance （CT/MR） registration post permanent implant of the prostate //Medical physics， 32 （ 2 ）： 473 - 482
Ruan D L ， Yan Y ， Chen S ， Xue J H and Wang H Z . 2020 . Deep disturbance-disentangled learning for facial expression recognition // Proceedings of the 28th ACM International Conference on Multimedia . Seattle， USA ： ACM： 2833 - 2841 ［ DOI： 10.1145/3394171.3413907 http://dx.doi.org/10.1145/3394171.3413907 ］
Sanchez E H ， Serrurier M and Ortner M . 2020 . Learning disentangled representations via mutual information estimation // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 205 - 221 ［ DOI： 10.1007/978-3-030-58542-6_13 http://dx.doi.org/10.1007/978-3-030-58542-6_13 ］
Sangkloy P ， Burnell N ， Ham C and Hays James . 2016 . The sketchy database： learning to retrieve badly drawn bunnies // ACM Transactions on Graphics （TOG） . 35 （ 4 ）： 1 - 12 ［ DOI： 10.1145/2897824.2925954 http://dx.doi.org/10.1145/2897824.2925954 ］
Schuldt C ， Laptev I and Caputo B . 2004 . Recognizing human actions： a local SVM approach // Proceedings of the 17th International Conference on Pattern Recognition . Cambridge， UK ： IEEE： 32 - 36 ［ DOI： 10.1109/ICPR.2004.1334462 http://dx.doi.org/10.1109/ICPR.2004.1334462 ］
Shen Z Q ， Huang M Y ， Shi J P ， Xue X Y and Huang T S . 2019 . Towards instance-level image-to-image translation // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 3683 - 3692
Singh K K ， Ojha U and Lee Y J . 2019 . FineGAN： unsupervised hierarchical disentanglement for fine-grained object generation and discovery // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 6483 - 6492 ［ DOI： 10.1109/CVPR.2019.00665 http://dx.doi.org/10.1109/CVPR.2019.00665 ］
Sønderby C K ， Raiko T ， Maaløe L ， Sønderby S K and Winther O . 2016 . Ladder variational autoencoders // Proceedings of the 30th International Conference on Neural Information Processing Systems . Barcelona， Spain ： Curran Associates Inc.： 3745 - 3753
Soomro K ， Zamir A R and Shah M . 2012 . UCF101： a dataset of 101 human actions classes from videos in the wild ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1212.0402.pdf https://arxiv.org/pdf/1212.0402.pdf
Sorrenson P ， Rother C and Köthe U . 2020 . Disentanglement by nonlinear ICA with general incompressible-flow networks （GIN） ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/2001.04872.pdf https://arxiv.org/pdf/2001.04872.pdf
Srivastava N ， Mansimov E and Salakhutdinov R . 2015 . Unsupervised learning of video representations using LSTMs // Proceedings of the 32nd International Conference on Machine Learning . Lille， France ： JMLR.org： 843 - 852
Sun H L ， Mehta R ， Zhou H ， Huang Z C ， Johnson S ， Prabhakaran V and Singh V . 2019a . DUAL-GLOW： conditional flow-based generative model for modality transfer // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 10610 - 10619 ［ DOI： 10.1109/ICCV.2019.01071 http://dx.doi.org/10.1109/ICCV.2019.01071 ］
Sun Y ， Ye Y ， Liu W ， Gao W P ， Fu Y L and Mei T . 2019b . Human mesh recovery from monocular images via a skeleton-disentangled representation // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 5348 - 5357 ［ DOI： 10.1109/ICCV.2019.00545 http://dx.doi.org/10.1109/ICCV.2019.00545 ］
Tong B ， Wang C ， Klinkigt M ， Kobayashi Y and Nonaka Y . 2019 . Hierarchical disentanglement of discriminative latent features for zero-shot learning // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 11459 - 11468 ［ DOI： 10.1109/CVPR.2019.01173 http://dx.doi.org/10.1109/CVPR.2019.01173 ］
Tran L ， Yin X and Liu X M . 2017 . Disentangled representation learning GAN for pose-invariant face recognition // Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu， USA ： IEEE： 1283 - 1292 ［ DOI： 10.1109/CVPR.2017.141 http://dx.doi.org/10.1109/CVPR.2017.141 ］
Tsai Y H H ， Liang P P ， Zadeh A ， Morency L P and Salakhutdinov R . 2019 . Learning factorized multimodal representations ［EB/OL］.［ 2022-01-21 ］. https://arxiv.org/pdf/1806.06176.pdf https://arxiv.org/pdf/1806.06176.pdf
Tulyakov S ， Liu M Y ， Yang X D and Kautz J . 2018 . MoCoGAN： decomposing motion and content for video generation // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 1526 - 1535 ［ DOI： 10.1109/CVPR.2018.00165 http://dx.doi.org/10.1109/CVPR.2018.00165 ］
Van Steenkiste S ， Locatello F ， Schmidhuber J and Bachem O . 2019 . Are disentangled representations helpful for abstract visual reasoning？ // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates， Inc.： 14245 - 14258
Wah C ， Branson S ， Welinder P ， Perona P and Belongie S . 2011 . The Caltech-UCSD Birds-200-2011 Dataset . California Institute of Technology
Wang G Q ， Han H ， Shan S G and Chen X L . 2020a . Cross-domain face presentation attack detection via multi-domain disentangled representation learning // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 6677 - 6686 ［ DOI： 10.1109/CVPR42600.2020.00671 http://dx.doi.org/10.1109/CVPR42600.2020.00671 ］
Wang H ， Deng C ， Liu T and Tao D . 2021 . Transferable coupled network for zero-shot sketch-based image retrieval . IEEE Transactions on Pattern Analysis and Machine Intelligence . 44 （ 12 ）： 9181 - 9194 ［ DOI： 10.1109/TPAMI.2021.3123315 http://dx.doi.org/10.1109/TPAMI.2021.3123315 ］
Wang W J ， Shi Y F ， Chen S M ， Peng Q M ， Zheng F and You X G . 2021 . Norm-guided adaptive visual embedding for zero-shot sketch-based image retrieval // Proceedings of the 30th International Joint Conference on Artificial Intelligence . 2021： 1106 - 1112 ［ DOI： 10.24963/ijcai.2021/153 http://dx.doi.org/10.24963/ijcai.2021/153 ］
Wang Y H ， Bilinski P ， Bremond F and Dantcheva A . 2020b . G 3 AN： disentangling appearance and motion for video generation// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA： IEEE： 5263 - 5272 ［ DOI： 10.1109/CVPR42600.2020.00531 http://dx.doi.org/10.1109/CVPR42600.2020.00531 ］
Wei L ， Zhang S ， Gao W and Tian Q . 2018 . Person transfer GAN to bridge domain gap for person re-identification // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 79 - 88
Wu R L and Lu S J . 2020 . LEED： label-free expression editing via disentanglement // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 781 - 798 ［ DOI： 10.1007/978-3-030-58610-2_46 http://dx.doi.org/10.1007/978-3-030-58610-2_46 ］
Wu S ， Deng G C ， Li J C ， Li R ， Yu Z W and Wong H S . 2019 . Enhancing TripleGAN for semi-supervised conditional instance synthesis and classification // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 10091 - 10100
Xiao F Y ， Liu H T and Lee Y J . 2019a . Identity from here， pose from there： self-supervised disentanglement and generation of objects using unlabeled videos // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 7012 - 7021 ［ DOI： 10.1109/ICCV.2019.00711 http://dx.doi.org/10.1109/ICCV.2019.00711 ］
Xiao H ， Rasul K and Vollgraf R . 2017 . Fashion-MNIST： a novel image dataset for benchmarking machine learning algorithms ［EB/OL］. ［ 2022-01-21 ］. https://arxiv.org/pdf/1708.07747.pdf https://arxiv.org/pdf/1708.07747.pdf
Xiao J ， Liao L ， Liu Q G and Hu R M . 2019b . CISI-net： explicit latent content inference and imitated style rendering for image inpainting . Proceedings of 2019 AAAI Conference on Artificial Intelligence ， 33 （ 1 ）： 354 - 362 ［ DOI： 10.1609/aaai.v33i01.3301354 http://dx.doi.org/10.1609/aaai.v33i01.3301354 ］
Xu X X ， Yang M L ， Yang Y H and Wang H . 2021 . Progressive domain-independent feature decomposition network for zero-shot sketch-based image retrieval // Proceedings of the 29th International Joint Conference on Artificial Intelligence . Yokohama， Japan ： IJCAI.org： 984 - 990
Xuan S Y and Zhang S L . 2021 . Intra-inter camera similarity for unsupervised person re-identification // Proceedings of 2021 IEEE Conference on Computer Vision and Pattern Recognition . IEEE ： 11926 - 11935
Yang J L ， Dvornek N C ， Zhang F ， Chapiro J ， Lin M D and Duncan J S . 2019 . Unsupervised domain adaptation via disentangled representations： application to cross-modality liver segmentation // Proceedings of the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention . Shenzhen， China ： Springer： 255 - 263 ［ DOI： 10.1007/978-3-030-32245-8_29 http://dx.doi.org/10.1007/978-3-030-32245-8_29 ］
Yang J M ， Reed S ， Yang M H and Lee H . 2015 . Weakly-supervised disentangling with recurrent transformations for 3D view synthesis // Proceedings of the 28th International Conference on Neural Information Processing Systems . Montreal， Canada ： MIT Press： 1099 - 1107
Yang L L and Yao A . 2019 . Disentangling latent hands for image synthesis and pose estimation // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 9869 - 9878 ［ DOI： 10.1109/CVPR.2019.01011 http://dx.doi.org/10.1109/CVPR.2019.01011 ］
Yin G J ， Liu B ， Sheng L ， Yu N H ， Wang X G and Shao J . 2019 . Semantics disentangling for text-to-image generation // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 2322 - 2331 ［ DOI： 10.1109/CVPR.2019.00243 http://dx.doi.org/10.1109/CVPR.2019.00243 ］
Yu X M ， Chen Y Q ， Li T ， Liu S and Li G . 2019 . Multi-mapping image-to-image translation via learning disentanglement // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver， Canada ： Curran Associates， Inc.： 2994 - 3004
Yu X M ， Ying Z Q ， Li T ， Liu S and Li G . 2018 . Multi-mapping image-to-image translation with central biasing normalization ［EB/OL］.［ 2022-01-21 ］. https://arxiv.org/pdf/1806.10050.pdf https://arxiv.org/pdf/1806.10050.pdf
Zang X H ， Li G ， Gao W and Shu X J . 2021 . Learning to disentangle scenes for person re-identification . Image and Vision Computing . 116 ： # 104330 ［ DOI： 10.1016/j.imavis.2021.104330 http://dx.doi.org/10.1016/j.imavis.2021.104330 ］
Zhang J F ， Huang Y Y ， Li Y Y ， Zhao W J and Zhang L Q . 2019a . Multi-attribute transfer via disentangled representation . Proceedings of 2019 AAAI Conference on Artificial Intelligence ， 33 （ 1 ）： 9195 - 9202 ［ DOI： 10.1609/aaai.v33i01.33019195 http://dx.doi.org/10.1609/aaai.v33i01.33019195 ］
Zhang K Y ， Yao T P ， Zhang J ， Tai Y ， Ding S H ， Li J L ， Huang F Y ， Song H C and Ma L Z . 2020 . Face anti-spoofing via disentangled representation learning // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 641 - 657 ［ DOI： 10.1007/978-3-030-58529-7_38 http://dx.doi.org/10.1007/978-3-030-58529-7_38 ］
Zhang Z Y ， Tran L ， Yin X ， Atoum Y ， Liu X M ， Wan J and Wang N X . 2019b . Gait recognition via disentangled representation learning // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 4705 - 4714 ［ DOI： 10.1109/CVPR.2019.00484 http://dx.doi.org/10.1109/CVPR.2019.00484 ］
Zhao J ， Cheng Y ， Cheng Y ， Yang Y ， Zhao F ， Li J S ， Liu H Z ， Yan S C and Feng J S . 2019 . Look across elapse： disentangled representation learning and photorealistic cross-age face synthesis for age-invariant face recognition . Proceedings of 2019 AAAI Conference on Artificial Intelligence ， 33 （ 1 ）： 9251 - 9258 ［ DOI： 10.1609/aaai.v33i01.33019251 http://dx.doi.org/10.1609/aaai.v33i01.33019251 ］
Zhao S J ， Song J M and Ermon S . 2017 . Learning hierarchical features from deep generative models // Proceedings of the 34th International Conference on Machine Learning . Sydney， Australia ： JMLR.org： 4091 - 4099
Zhao Y ， Xiong Y J and Lin D H . 2018 . Recognize actions by disentangling components of dynamics // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 6566 - 6575 ［ DOI： 10.1109/CVPR.2018.00687 http://dx.doi.org/10.1109/CVPR.2018.00687 ］
Zheng L ， Shen L ， Tian L ， Wang S ， Wang J and Tian Q . 2015 . Scalable person re-identification： a benchmark // Proceedings of 2015 IEEE International Conference on Computer Vision （ICCV） . Santiago， Chile ： IEEE： 1116 - 1124
Zheng Z ， Zheng L and Yang Y . 2017 . Unlabeled samples generated by GAN improve the person re-identification baseline in vitro // Proceedings of 2017 IEEE International Conference on Computer Vision . Venice， Italy ： IEEE： 3754 - 3762
Zheng Z ， Yang X ， Yu Z ， Zheng L ， Yang Y and Kautz J . 2019 . Joint discriminative and generative learning for person re-identification // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 2138 - 2147
Zhu J Y ， Park T ， Isola P and Efros A A . 2017 . Unpaired image-to-image translation using cycle-consistent adversarial networks // Proceedings of 2017 IEEE International Conference on Computer Vision . Venice， Italy ： IEEE： 2242 - 2251 ［ DOI： 10.1109/ICCV.2017.244 http://dx.doi.org/10.1109/ICCV.2017.244 ］
Zhu J Y ， Zhang Z T ， Zhang C K ， Wu J J ， Torralba A ， Tenenbaum J B and Freeman W T . 2018 . Visual object networks： image generation with disentangled 3D representation // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Montreal， Canada ： Curran Associates Inc.： 118 - 129
Zhu X Q ， Xu C and Tao D C . 2020a . Learning disentangled representations with latent variation predictability // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 684 - 700 ［ DOI： 10.1007/978-3-030-58607-2_40 http://dx.doi.org/10.1007/978-3-030-58607-2_40 ］
Zhu Y Z ， Min M R ， Kadav A and Graf H P . 2020b . S3VAE： self-supervised sequential VAE for representation disentanglement and data generation // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 6537 - 6546 ［ DOI： 10.1109/CVPR42600.2020.00657 http://dx.doi.org/10.1109/CVPR42600.2020.00657 ］
Zhu Z Y ， Luo P ， Wang X G and Tang X O . 2014 . Multi-view perceptron： a deep model for learning face identity and view representations // Proceedings of the 27th International Conference on Neural Information Processing Systems . Montreal， Canada ： MIT Press： 217 - 225
Zou Y ， Yang X D ， Yu Z D ， Vijaya Kumar B V K and Kautz J . 2020 . Joint disentangling and adaptation for cross-domain person re-identification // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 87 - 104 ［ DOI： 10.1007/978-3-030-58536-5_6 http://dx.doi.org/10.1007/978-3-030-58536-5_6 ］
Zwicker M ， Hu Q Y ， Szabó A ， Portenier T and Favaro P . 2018 . Disentangling factors of variation by mixing them // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 3399 - 3407 ［ DOI： 10.1109/CVPR.2018.00358 http://dx.doi.org/10.1109/CVPR.2018.00358 ］
相关文章
相关作者
相关机构
京公网安备11010802024621
