{"url":"/method/nvae","slug":"nvae","name":"NVAE","full_name":"Nouveau VAE","full_name_withheld":false,"description_markdown":"**NVAE**, or **Nouveau VAE**, is deep, hierarchical variational autoencoder. It can be trained with the original [VAE](https://paperswithcode.com/method/vae) objective, unlike alternatives such as [VQ-VAE-2](https://paperswithcode.com/method/vq-vae-2). NVAE’s design focuses on tackling two main challenges: (i) designing expressive neural\r\nnetworks specifically for VAEs, and (ii) scaling up the training to a large number of hierarchical\r\ngroups and image sizes while maintaining training stability.\r\n\r\nTo tackle long-range correlations in the data, the model employs hierarchical multi-scale modelling. The generative model starts from a small spatially arranged latent variables as $\\mathbf{z}\\_{1}$ and samples from the hierarchy group-by-group while gradually doubling the spatial dimensions. This multi-scale approach enables NVAE to capture global long-range correlations at the top of the hierarchy and local fine-grained dependencies at the lower groups.\r\n\r\nAdditional design choices include the use of residual cells for the generative models and the encoder, which employ a number of tricks and modules to achieve good performance, and the use of residual normal distributions to smooth optimization. See the components section for more details.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2007.03898v3","title":"NVAE: A Deep Hierarchical Variational Autoencoder","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck","date":"2022-07-27","arxiv_id":"2207.13529","n_code_links":0,"syntology":null},{"paper":"/paper/defending-variational-autoencoders-from","title":"Alleviating Adversarial Attacks on Variational Autoencoders with MCMC","date":"2022-03-18","arxiv_id":"2203.09940","n_code_links":1,"syntology":null},{"paper":"/paper/polarity-sampling-quality-and-diversity","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","date":"2022-03-03","arxiv_id":"2203.01993","n_code_links":1,"syntology":null},{"paper":null,"title":"NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection","date":"2021-01-08","arxiv_id":"2101.02908","n_code_links":0,"syntology":null},{"paper":"/paper/nvae-a-deep-hierarchical-variational","title":"NVAE: A Deep Hierarchical Variational Autoencoder","date":"2020-07-08","arxiv_id":"2007.03898","n_code_links":10,"syntology":{"ran":23,"of":41,"unverified":18,"pointer_only":23}}],"papers_shown":5,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/time-series-1","name":"Time Series","papers":1},{"task":"/task/time-series","name":"Time Series Analysis","papers":1},{"task":"/task/time-series-anomaly-detection","name":"Time Series Anomaly Detection","papers":1},{"task":"/task/unconditional-image-generation","name":"Unconditional Image Generation","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/nvae"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}