mlsanityData to 7 Oct 2026

Training Invertible Neural Networks as Autoencoders

arXiv 2303.11239 ↗First posted 20 Mar 2023cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work, we present methods to train Invertible Neural Networks (INNs) as (variational) autoencoders which we call INN (variational) autoencoders. Our experiments on MNIST, CIFAR and CelebA show that for low bottleneck sizes our INN autoencoder achieves results similar to the classical autoencoder. However, for large bottleneck sizes our INN autoencoder outperforms its classical counterpart. Based on the empirical results, we hypothesize that INN autoencoders might not have any intrinsic information loss and thereby are not bounded to a maximal number of layers (depth) after which only suboptimal results can be achieved.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

31 of 39 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2015Fast R-CNNcited by 2,930
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  10. 2016Variational Inference: A Review for Statisticianscited by 1,466
  11. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  12. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
19 more
  1. 2016Deep Variational Information Bottleneckcited by 915
  2. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  3. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  4. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  5. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
  6. 2016Tutorial on Variational Autoencoderscited by 404
  7. 2018Invertible Residual Networkscited by 364
  8. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  9. 2016Adversarially Learned Inferencecited by 216
  10. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 215
  11. 2018i-RevNet: Deep Invertible Networkscited by 137
  12. 2018Excessive Invariance Causes Adversarial Vulnerabilitycited by 66
  13. 2018Understanding Convolutional Neural Networks with Information Theory: An Initial Explorationcited by 31
  14. 2018Understanding Autoencoders with Information Theoretic Conceptscited by 29
  15. 2017Semantically Decomposing the Latent Spaces of Generative Adversarial Networkscited by 19
  16. 2018Invertible Autoencoder for domain adaptationcited by 10
  17. 2018Analysis of Invariance and Robustness via Invertibility of ReLU-Networkscited by 5
  18. 2017Comparison of Maximum Likelihood and GAN-based training of Real NVPscited by 2
  19. 2018Training Generative Reversible Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 2.

4 papers.

  1. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 12
  2. 2024Optimizing Retinal Prosthetic Stimuli with Conditional Invertible Neural Networkscited by 1
  3. 2026Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectracited by 0
  4. 2026Deep Invertible Autoencoders for Dimensionality Reduction of Dynamical Systemscited by 0