{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:49:45Z","timestamp":1743144585444,"version":"3.40.3"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730122"},{"type":"electronic","value":"9783031730139"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73013-9_19","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:53:33Z","timestamp":1732607613000},"page":"326-344","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Energy-Calibrated VAE with\u00a0Test Time Free Lunch"],"prefix":"10.1007","author":[{"given":"Yihong","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siya","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjian","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"19_CR1","unstructured":"Aneja, J., Schwing, A., Kautz, J., Vahdat, A.: A contrastive learning approach for training variational autoencoder priors. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"19_CR2","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a070, pp. 214\u2013223. PMLR (2017). https:\/\/proceedings.mlr.press\/v70\/arjovsky17a.html"},{"key":"19_CR3","unstructured":"Chamon, L.F., Paternain, S., Calvo-Fullana, M., Ribeiro, A.: Constrained learning with non-convex losses. arXiv:2103.05134 (2021)"},{"key":"19_CR4","unstructured":"Chrabaszcz, P., Loshchilov, I., Hutter, F.: A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv abs\/1707.08819 (2017). https:\/\/api.semanticscholar.org\/CorpusID:7304542"},{"key":"19_CR5","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: AISTATS, pp. 215\u2013223 (2011)"},{"key":"19_CR6","unstructured":"Cui, J., Han, T.: Learning energy-based model via dual-MCMC teaching. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"19_CR7","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009). https:\/\/doi.org\/10.1109\/cvpr.2009.5206848","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"19_CR8","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: NICE: non-linear independent components estimation. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Workshop Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1410.8516"},{"key":"19_CR9","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"19_CR10","unstructured":"Du, Y., Mordatch, I.: Implicit generation and modeling with energy based models. In: Advances in Neural Information Processing Systems, pp. 3608\u20133618 (2019)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Gao, R., Nijkamp, E., Kingma, D.P., Xu, Z., Dai, A.M., Wu, Y.N.: Flow contrastive estimation of energy-based models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7518\u20137528 (2020)","DOI":"10.1109\/CVPR42600.2020.00754"},{"key":"19_CR12","unstructured":"Gao, R., Song, Y., Poole, B., Wu, Y.N., Kingma, D.P.: Learning energy-based models by diffusion recovery likelihood. arXiv preprint arXiv:2012.08125 (2020)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Gong, X., Chang, S., Jiang, Y., Wang, Z.: AutoGAN: neural architecture search for generative adversarial networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00332"},{"key":"19_CR14","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Han, T., Nijkamp, E., Zhou, L., Pang, B., Zhu, S.C., Wu, Y.N.: Joint training of variational auto-encoder and latent energy-based model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7978\u20137987 (2020)","DOI":"10.1109\/CVPR42600.2020.00800"},{"key":"19_CR16","unstructured":"He, H., Wang, H., Lee, G.H., Tian, Y.: ProbGAN: towards probabilistic GAN with theoretical guarantees. In: ICLR (2019)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR18","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"key":"19_CR19","unstructured":"Hill, M., Nijkamp, E., Mitchell, J.C., Pang, B., Zhu, S.C.: Learning probabilistic models from generator latent spaces with hat EBM. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=AluQNIIb_Zy"},{"key":"19_CR20","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arXiv:2006.11239 (2020)"},{"key":"19_CR21","unstructured":"Huang, H., He, R., Sun, Z., Tan, T., et\u00a0al.: Introvae: introspective variational autoencoders for photographic image synthesis. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"19_CR22","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs\/1502.03167 (2015). http:\/\/arxiv.org\/abs\/1502.03167"},{"key":"19_CR23","unstructured":"Jonathan, H., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"19_CR24","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018)"},{"key":"19_CR25","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. arXiv preprint arXiv:2006.06676 (2020)"},{"key":"19_CR26","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"19_CR27","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible $$1 \\times 1$$ convolutions. arXiv preprint arXiv:1807.03039 (2018)"},{"key":"19_CR28","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: The International Conference on Learning Representations (ICLR) (2014)"},{"key":"19_CR29","unstructured":"Kingma, D.P., Welling, M.: Stochastic gradient VB and the variational auto-encoder. In: Second International Conference on Learning Representations, ICLR, vol.\u00a019, p.\u00a0121 (2014)"},{"key":"19_CR30","unstructured":"Kong, Z., Chaudhuri, K.: The expressive power of a class of normalizing flow models. In: International Conference on Artificial Intelligence and Statistics (2020)"},{"key":"19_CR31","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Aittala, M., Aila, T., Lehtinen, J.: The role of imagenet classes in fr\u00e9chet inception distance. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=4oXTQ6m_ws8"},{"key":"19_CR32","unstructured":"Lee, H., Jeong, J., Park, S., Shin, J.: Guiding energy-based models via contrastive latent variables. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=CZmHHj9MgkP"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Chang, C.C., Chen, Y.S., Juan, D.C., Wei, W., Chen, H.T.: Coco-GAN: generation by parts via conditional coordinating. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4512\u20134521 (2019)","DOI":"10.1109\/ICCV.2019.00461"},{"key":"19_CR34","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=PqvMRDCJT9t"},{"key":"19_CR35","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":"19_CR36","doi-asserted-by":"crossref","unstructured":"Menon, S., Damian, A., Hu, S., Ravi, N., Rudin, C.: Pulse: self-supervised photo upsampling via latent space exploration of generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2437\u20132445 (2020)","DOI":"10.1109\/CVPR42600.2020.00251"},{"key":"19_CR37","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: ICLR (2018)"},{"key":"19_CR38","unstructured":"Nielsen, D., Jaini, P., Hoogeboom, E., Winther, O., Welling, M.: Survae flows: surjections to bridge the gap between VAEs and flows. In: NeurIPS (2020)"},{"key":"19_CR39","unstructured":"van\u00a0den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., Kavukcuoglu, K.: Conditional image generation with pixelcnn decoders (2016)"},{"key":"19_CR40","unstructured":"Parimala, K., Channappayya, S.: Quality aware generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 2948\u20132958 (2019)"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Parmar, G., Li, D., Lee, K., Tu, Z.: Dual contradistinctive generative autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 823\u2013832 (2021)","DOI":"10.1109\/CVPR46437.2021.00088"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Pidhorskyi, S., Adjeroh, D.A., Doretto, G.: Adversarial latent autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14104\u201314113 (2020)","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"19_CR43","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models (2023)"},{"key":"19_CR44","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, pp. 11918\u201311930 (2019)"},{"key":"19_CR45","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. arXiv preprint arXiv:2006.09011 (2020)"},{"key":"19_CR46","unstructured":"Tomczak, J.M., Welling, M.: VAE with a vampprior. In: Storkey, A.J., P\u00e9rez-Cruz, F. (eds.) International Conference on Artificial Intelligence and Statistics, AISTATS 2018, Playa Blanca, Lanzarote, Canary Islands, Spain, 9\u201311 April 2018. Proceedings of Machine Learning Research, vol.\u00a084, pp. 1214\u20131223. PMLR (2018). http:\/\/proceedings.mlr.press\/v84\/tomczak18a.html"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167\u20137176 (2017)","DOI":"10.1109\/CVPR.2017.316"},{"key":"19_CR48","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. In: Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"19_CR49","unstructured":"Wang, W., Sun, Y., Halgamuge, S.: Improving MMD-GAN training with repulsive loss function. In: ICLR (2019)"},{"key":"19_CR50","unstructured":"Wang, Y., Yu, J., Zhang, J.: Zero-shot image restoration using denoising diffusion null-space model. In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=mRieQgMtNTQ"},{"key":"19_CR51","unstructured":"Xiao, Z., Kreis, K., Kautz, J., Vahdat, A.: VAEBM: a symbiosis between variational autoencoders and energy-based models. In: International Conference on Learning Representations (2021)"},{"key":"19_CR52","unstructured":"Xiao, Z., Yan, Q., Chen, Y., Amit, Y.: Generative latent flow: a framework for non-adversarial image generation. CoRR abs\/1905.10485 (2019). http:\/\/arxiv.org\/abs\/1905.10485"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Xie, J., Lu, Y., Gao, R., Wu, Y.N.: Cooperative learning of energy-based model and latent variable model via MCMC teaching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11834"},{"key":"19_CR54","unstructured":"Xie, J., Lu, Y., Zhu, S.C., Wu, Y.: A theory of generative convnet. In: International Conference on Machine Learning, pp. 2635\u20132644 (2016)"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Xie, J., Zheng, Z., Li, P.: Learning energy-based model with variational auto-encoder as amortized sampler. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 10441\u201310451 (2021)","DOI":"10.1609\/aaai.v35i12.17250"},{"key":"19_CR56","unstructured":"Xie, J., Zhu, Y., Li, J., Li, P.: A tale of two flows: Cooperative learning of langevin flow and normalizing flow toward energy-based model. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=31d5RLCUuXC"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: Pointflow: 3D point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"19_CR58","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)"},{"key":"19_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"19_CR60","unstructured":"Zhao, Y., Xie, J., Li, P.: Learning energy-based generative models via coarse-to-fine expanding and sampling. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=aD1_5zowqV"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73013-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:31:10Z","timestamp":1732609870000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73013-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031730122","9783031730139"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73013-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}