mlsanityData to 14 Oct 2026

CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse

arXiv 2309.02968 ↗First posted 6 Sep 2023cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The Variational Autoencoder (VAE) is known to suffer from the phenomenon of textitposterior collapse, where the latent representations generated by the model become independent of the inputs. This leads to degenerated representations of the input, which is attributed to the limitations of the VAE's objective function. In this work, we propose a novel solution to this issue, the Contrastive Regularization for Variational Autoencoders (CR-VAE). The core of our approach is to augment the original VAE with a contrastive objective that maximizes the mutual information between the representations of similar visual inputs. This strategy ensures that the information flow between the input and its latent representation is maximized, effectively avoiding posterior collapse. We evaluate our method on a series of visual datasets and demonstrate, that CR-VAE outperforms state-of-the-art approaches in preventing posterior collapse.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 6 Sep 2023.

Builds on

25 of 42 references.

References · 25

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  6. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  7. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  8. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  9. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  10. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  11. 2015Generating Sentences from a Continuous Spacecited by 612
  12. 2015Importance Weighted Autoencoderscited by 456
13 more
  1. 2017EMNIST: an extension of MNIST to handwritten letterscited by 213
  2. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  3. 2016Variational Lossy Autoencodercited by 176
  4. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 142
  5. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
  6. 2018Semi-Amortized Variational Autoencoderscited by 83
  7. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  8. 2018Avoiding Latent Variable Collapse With Generative Skip Modelscited by 47
  9. 2021Return-Based Contrastive Representation Learning for Reinforcement Learningcited by 36
  10. 2022On the Generalization of Representations in Reinforcement Learningcited by 28
  11. 2019Learning Representations by Maximizing Mutual Information in Variational Autoencoderscited by 20
  12. 2020A Tutorial on VAEs: From Bayes' Rule to Lossless Compressioncited by 11
  13. 2022Forget-me-not! Contrastive Critics for Mitigating Posterior Collapsecited by 6

Built on by

Cited by year

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

4 papers.

  1. 2023PcLast: Discovering Plannable Continuous Latent Statescited by 4
  2. 2025A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learningcited by 2
  3. 2024ED-VAE: Entropy Decomposition of ELBO in Variational Autoencoderscited by 1
  4. 2025Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEscited by 0