{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T15:34:54Z","timestamp":1760369694400,"version":"3.40.3"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695378"},{"type":"electronic","value":"9783030695385"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69538-5_39","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T21:16:40Z","timestamp":1614201400000},"page":"643-660","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["dpVAEs: Fixing Sample Generation for Regularized VAEs"],"prefix":"10.1007","author":[{"given":"Riddhish","family":"Bhalodia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iain","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shireen","family":"Elhabian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Zhao, S., Song, J., Ermon, S.: Infovae: balancing learning and inference in variational autoencoders. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5885\u20135892 (2019)","DOI":"10.1609\/aaai.v33i01.33015885"},{"key":"39_CR2","first-page":"6","volume":"2","author":"I Higgins","year":"2017","unstructured":"Higgins, I., et al.: beta-vae: learning basic visual concepts with a constrained variational framework. ICLR 2, 6 (2017)","journal-title":"ICLR"},{"key":"39_CR3","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: International Conference on Machine Learning, pp. 2654\u20132663 (2018)"},{"key":"39_CR4","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172\u20132180 (2016)"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.: Plug & play generative networks: conditional iterative generation of images in latent space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4467\u20134477 (2017)","DOI":"10.1109\/CVPR.2017.374"},{"key":"39_CR6","unstructured":"Mathieu, M.F., Zhao, J.J., Zhao, J., Ramesh, A., Sprechmann, P., LeCun, Y.: Disentangling factors of variation in deep representation using adversarial training. In: Advances in Neural Information Processing Systems, pp. 5040\u20135048 (2016)"},{"key":"39_CR7","unstructured":"Higgins, I., et al.: Darla: Improving zero-shot transfer in reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, JMLR. org, pp. 1480\u20131490 (2017)"},{"key":"39_CR8","unstructured":"Rezende, D., Danihelka, I., Gregor, K., Wierstra, D., et al.: One-shot generalization in deep generative models. In: International Conference on Machine Learning, pp. 1521\u20131529 (2016)"},{"key":"39_CR9","unstructured":"Kingma, D.P., Mohamed, S., Rezende, D.J., Welling, M.: Semi-supervised learning with deep generative models. In: Advances in Neural Information Processing Systems, pp. 3581\u20133589 (2014)"},{"key":"39_CR10","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR11","unstructured":"Alemi, A., Poole, B., Fischer, I., Dillon, J., Saurous, R.A., Murphy, K.: Fixing a broken elbo. In: International Conference on Machine Learning, pp. 159\u2013168 (2018)"},{"key":"39_CR12","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.tics.2006.05.002","volume":"10","author":"A Yuille","year":"2006","unstructured":"Yuille, A., Kersten, D.: Vision as Bayesian inference: analysis by synthesis? Trends Cogn. Sci. 10, 301\u2013308 (2006)","journal-title":"Trends Cogn. Sci."},{"key":"39_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/978-3-540-87536-9_99","volume-title":"Artificial Neural Networks - ICANN 2008","author":"V Nair","year":"2008","unstructured":"Nair, V., Susskind, J., Hinton, G.E.: Analysis-by-synthesis by learning to invert generative black boxes. In: K\u016frkov\u00e1, V., Neruda, R., Koutn\u00edk, J. (eds.) ICANN 2008. LNCS, vol. 5163, pp. 971\u2013981. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-87536-9_99"},{"key":"39_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. ICLR (2014)"},{"key":"39_CR15","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning, pp. 1278\u20131286 (2014)"},{"key":"39_CR16","unstructured":"Maal\u00f8e, L., S\u00f8nderby, C.K., S\u00f8nderby, S.K., Winther, O.: Auxiliary deep generative models. In: International Conference on Machine Learning, pp. 1445\u20131453 (2016)"},{"key":"39_CR17","unstructured":"S\u00f8nderby, C.K., Raiko, T., Maal\u00f8e, L., S\u00f8nderby, S.K., Winther, O.: How to train deep variational autoencoders and probabilistic ladder networks. In: 33rd International Conference on Machine Learning (ICML 2016) (2016)"},{"key":"39_CR18","unstructured":"Pu, Y., et al.: Variational autoencoder for deep learning of images, labels and captions. In: Advances in Neural Information Processing Systems, pp. 2352\u20132360 (2016)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Xu, W., Sun, H., Deng, C., Tan, Y.: Variational autoencoder for semi-supervised text classification. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10966"},{"key":"39_CR20","unstructured":"Tschannen, M., Bachem, O., Lucic, M.: Recent advances in autoencoder-based representation learning. In: Third workshop on Bayesian Deep Learning (NeurIPS 2018) (2018)"},{"key":"39_CR21","unstructured":"Chen, X., et al.: Variational lossy autoencoder. ICLR (2017)"},{"key":"39_CR22","unstructured":"Hoffman, M.D., Johnson, M.J.: Elbo surgery: yet another way to carve up the variational evidence lower bound. In: Workshop in Advances in Approximate Bayesian Inference, NIPS, vol. 1. (2016)"},{"key":"39_CR23","unstructured":"Chen, T.Q., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: Advances in Neural Information Processing Systems, pp. 2610\u20132620 (2018)"},{"key":"39_CR24","unstructured":"Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. In: ICLR (2018)"},{"key":"39_CR25","unstructured":"Makhzani, A., Frey, B.J.: Pixelgan autoencoders. In: Advances in Neural Information Processing Systems, pp. 1975\u20131985 (2017)"},{"key":"39_CR26","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. In: ICLR (2016)"},{"key":"39_CR27","unstructured":"Rosca, M., Lakshminarayanan, B., Mohamed, S.: Distribution matching in variational inference. arXiv preprint arXiv:1802.06847 (2018)"},{"key":"39_CR28","unstructured":"Xu, H., Chen, W., Lai, J., Li, Z., Zhao, Y., Pei, D.: On the necessity and effectiveness of learning the prior of variational auto-encoder. arXiv preprint arXiv:1905.13452 (2019)"},{"key":"39_CR29","unstructured":"Shmelkov, K., Lucas, T., Alahari, K., Schmid, C., Verbeek, J.: Coverage and quality driven training of generative image models. arXiv preprint arXiv:1901.01091 (2019)"},{"key":"39_CR30","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"39_CR31","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International conference on machine learning, pp. 214\u2013223 (2017)"},{"key":"39_CR32","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1007\/s10463-011-0343-8","volume":"64","author":"M Sugiyama","year":"2012","unstructured":"Sugiyama, M., Suzuki, T., Kanamori, T.: Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation. Ann. Inst. Stat. Math. 64, 1009\u20131044 (2012)","journal-title":"Ann. Inst. Stat. Math."},{"key":"39_CR33","unstructured":"Mescheder, L., Nowozin, S., Geiger, A.: Adversarial variational bayes: Unifying variational autoencoders and generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, JMLR. org, pp. 2391\u20132400 (2017)"},{"key":"39_CR34","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. arXiv preprint arXiv:1511.05644 (2015)"},{"key":"39_CR35","unstructured":"Srivastava, A., Valkov, L., Russell, C., Gutmann, M.U., Sutton, C.: Veegan: Reducing mode collapse in gans using implicit variational learning. In: Advances in Neural Information Processing Systems, pp. 3308\u20133318 (2017)"},{"key":"39_CR36","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. In: International Conference on Learning Representations (2016)"},{"key":"39_CR37","unstructured":"Tolstikhin, I., Bousquet, O., Gelly, S., Schoelkopf, B.: Wasserstein auto-encoders. arXiv preprint arXiv:1711.01558 (2017)"},{"key":"39_CR38","unstructured":"Xiao, Z., Yan, Q., Amit, Y.: Generative latent flow. arXiv preprint arXiv:1905.10485 (2019)"},{"key":"39_CR39","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improved variational inference with inverse autoregressive flow. In: Advances in neural information processing systems, pp. 4743\u20134751(2016)"},{"key":"39_CR40","unstructured":"Bauer, M., Mnih, A.: Resampled priors for variational autoencoders. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 66\u201375 (2019)"},{"key":"39_CR41","unstructured":"Tomczak, J., Welling, M.: Vae with a vampprior. In: International Conference on Artificial Intelligence and Statistics, pp. 1214\u20131223 (2018)"},{"key":"39_CR42","unstructured":"Dilokthanakul, N., et al.: Deep unsupervised clustering with Gaussian mixture variational autoencoders. arXiv preprint arXiv:1611.02648 (2016)"},{"key":"39_CR43","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D., Wierstra, D.: Draw: a recurrent neural network for image generation. In: International Conference on Machine Learning, pp. 1462\u20131471(2015)"},{"key":"39_CR44","unstructured":"Gulrajani, I., et al.: Pixelvae: a latent variable model for natural images. In: ICLR (2017)"},{"key":"39_CR45","unstructured":"Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, pp. 6306\u20136315 (2017)"},{"key":"39_CR46","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. In: Advances in Neural Information Processing Systems, pp. 14866\u201314876 (2019)"},{"key":"39_CR47","unstructured":"Van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et al.: Conditional image generation with pixelcnn decoders. In: Advances in Neural Information Processing Systems, pp. 4790\u20134798 (2016)"},{"key":"39_CR48","unstructured":"Oord, A.v.d., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016)"},{"key":"39_CR49","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: Non-linear independent components estimation (2014)"},{"key":"39_CR50","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real nvp. In: ICLR (2017)"},{"key":"39_CR51","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: Proceedings of the 32nd International Conference on Machine Learning. Volume 37 of Proceedings of Machine Learning Research., Lille, France, PMLR, pp. 1530\u20131538 (2015)"},{"key":"39_CR52","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: Generative flow with invertible 1 x 1 convolutions. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31, pp. 10215\u201310224. Curran Associates, Inc. (2018)"},{"key":"39_CR53","unstructured":"Huang, C.W., et al.: Learnable explicit density for continuous latent space and variational inference. arXiv preprint arXiv:1710.02248 (2017)"},{"key":"39_CR54","unstructured":"Das, H.P., Abbeel, P., Spanos, C.J.: Dimensionality reduction flows. arXiv preprint arXiv:1908.01686 (2019)"},{"key":"39_CR55","unstructured":"Gritsenko, A.A., Snoek, J., Salimans, T.: On the relationship between normalising flows and variational-and denoising autoencoders (2019)"},{"key":"39_CR56","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., Bengio, S.: Generating sentences from a continuous space. In: Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pp. 10\u201321 (2016)","DOI":"10.18653\/v1\/K16-1002"},{"key":"39_CR57","unstructured":"Burgess, C.P., et al.: Understanding disentangling in beta-vae. arXiv preprint arXiv:1804.03599 (2018)"},{"key":"39_CR58","unstructured":"Liu, Q., Wang, D.: Stein variational gradient descent: A general purpose Bayesian inference algorithm. In: Advances in Neural Information Processing Systems, pp. 2378\u20132386 (2016)"},{"key":"39_CR59","doi-asserted-by":"crossref","unstructured":"Gretton, A., Borgwardt, K., Rasch, M., Sch\u00f6lkopf, B., Smola, A.J.: A kernel method for the two-sample-problem. In: Advances in Neural Information Processing Systems, pp. 513\u2013520 (2007)","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"39_CR60","unstructured":"Li, Y., Swersky, K., Zemel, R.: Generative moment matching networks. In: International Conference on Machine Learning, pp. 1718\u20131727 (2015)"},{"key":"39_CR61","unstructured":"Dziugaite, G.K., Roy, D.M., Ghahramani, Z.: Training generative neural networks via maximum mean discrepancy optimization. In: Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, pp. 258\u2013267. AUAI Press (2015)"},{"key":"39_CR62","unstructured":"LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010)"},{"key":"39_CR63","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)"},{"key":"39_CR64","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"39_CR65","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"39_CR66","unstructured":"Dinh, L., Sohl-Dickstein, J., Pascanu, R., Larochelle, H.: A RAD approach to deep mixture models. CoRR abs\/1903.07714 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69538-5_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T22:19:13Z","timestamp":1697926753000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69538-5_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695378","9783030695385"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69538-5_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}