Variational Autoencoders Without the Variation
Not on the map. Why?
Abstract (arXiv)
Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to explore the potential, for generative modelling, of removing the variational approach and returning to the classic deterministic autoencoder (DAE) with additional novel regularisation methods. In this paper we empirically explore the capability of DAEs for image generation without additional novel methods and the effect of the implicit regularisation and smoothness of large networks. We find that DAEs can be used successfully for image generation without additional loss terms, and that many of the useful properties of VAEs can arise implicitly from sufficiently large convolutional encoders and decoders when trained on CIFAR-10 and CelebA.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 1 Mar 2022.
Builds on
22 of 30 references.
References · 22
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2017Neural Discrete Representation Learningcited by 4,650
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
- 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
- 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
- 2017Wasserstein Auto-Encoderscited by 371
- 2018How Does Batch Normalization Help Optimization?cited by 355
10 more
- 2018Visual Reinforcement Learning with Imagined Goalscited by 248
- 2017VAE with a VampPriorcited by 247
- 2019Diagnosing and Enhancing VAE Modelscited by 192
- 2016Variational Lossy Autoencodercited by 175
- 2021A Universal Law of Robustness via Isoperimetrycited by 150
- 2020Implicit Gradient Regularizationcited by 145
- 2019From Variational to Deterministic Autoencoderscited by 131
- 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
- 2017Towards Deeper Understanding of Variational Autoencoding Modelscited by 56
- 2020Batch norm with entropic regularization turns deterministic autoencoders into generative modelscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.