mlsanityData to 14 Oct 2026

Denoising Criterion for Variational Auto-Encoding Framework

arXiv 1511.06406 ↗First posted 19 Nov 2015cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer that encourages this noise injection. In this paper, we show that injecting noise both in input and in the stochastic hidden layer can be advantageous and we propose a modified variational lower bound as an improved objective function in this setup. When input is corrupted, then the standard VAE lower bound involves marginalizing the encoder conditional distribution over the input noise, which makes the training criterion intractable. Instead, we propose a modified training criterion which corresponds to a tractable bound when input is corrupted. Experimentally, we find that the proposed denoising variational autoencoder (DVAE) yields better average log-likelihood than the VAE and the importance weighted autoencoder on the MNIST and Frey Face datasets.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 3; 2023: 11; 2024: 12; 2025: 2; 2026: 3.

43 papers.

Sort:

By area:

  1. 2021Illiterate DALL-E Learns to Composecited by 147
  2. 2023Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inferencecited by 42
  3. 2021Adversarial and Contrastive Variational Autoencoder for Sequential Recommendationcited by 28
  4. 2021My House, My Rules: Learning Tidying Preferences with Graph Neural Networkscited by 27
  5. 2021Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Priorcited by 24
  6. 2022Amortized Variational Inference: A Systematic Reviewcited by 16
  7. 2023Object-Centric Learning with Slot Mixture Modulecited by 11
  8. 2025Vector-Quantized Vision Foundation Models for Object-Centric Learningcited by 11
  9. 2023VTAE: Variational Transformer Autoencoder with Manifolds Learningcited by 10
  10. 2024Length-Aware Motion Synthesis via Latent Diffusioncited by 10
  11. 2021Mask-GVAE: Blind Denoising Graphs via Partitioncited by 9
  12. 2024Reasoning-Enhanced Object-Centric Learning for Videoscited by 7
31 more
  1. 2024Multi-Scale Fusion for Object Representationcited by 7
  2. 2021Exploring Versatile Prior for Human Motion via Motion Frequency Guidancecited by 5
  3. 2023Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Explorationcited by 5
  4. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5
  5. 2024Grouped Discrete Representation for Object-Centric Learningcited by 5
  6. 2022Latent Variable Models in the Era of Industrial Big Data: Extension and Beyondcited by 4
  7. 2024SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signalscited by 4
  8. 2021Blind Image Denoising and Inpainting Using Robust Hadamard Autoencoderscited by 2
  9. 2021PicTalky: Augmentative and Alternative Communication Software for Language Developmental Disabilitiescited by 2
  10. 2021Hybrid BYOL-ViT: Efficient approach to deal with small datasetscited by 2
  11. 2022Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decodercited by 2
  12. 2023Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Datacited by 2
  13. 2023Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learningcited by 2
  14. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  15. 2024SGW-based Multi-Task Learning in Vision Taskscited by 2
  16. 2021AASAE: Augmentation-Augmented Stochastic Autoencoderscited by 1
  17. 2023A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancycited by 1
  18. 2023inkn'hue: Enhancing Manga Colorization from Multiple Priors with Alignment Multi-Encoder VAEcited by 1
  19. 2024DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoisingcited by 1
  20. 2024Novel Hybrid Integrated Pix2Pix and WGAN Model with Gradient Penalty for Binary Images Denoisingcited by 1
  21. 2024Counterfactuals and Uncertainty-Based Explainable Paradigm for the Automated Detection and Segmentation of Renal Cysts in Computed Tomography Images: A Multi-Center Studycited by 1
  22. 2025Self-supervised Latent Space Optimization with Nebula Variational Codingcited by 1
  23. 2026MUFASA: A Multi-Layer Framework for Slot Attentioncited by 1
  24. 2021Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processingcited by 0
  25. 2021Window-Level is a Strong Denoising Surrogatecited by 0
  26. 2023Indeterminate Probability Theorycited by 0
  27. 2023Continuous Indeterminate Probability Neural Networkcited by 0
  28. 2024Quantifying User Coherence: A Unified Framework for Analyzing Recommender Systems Across Domainscited by 0
  29. 2024Diffusion Model from Scratchcited by 0
  30. 2026Learning-based Statistical Refinement for Denoisingcited by 0
  31. 2026A Multi-stage Constrained Optimization Framework for Data-driven Problemscited by 0