mlsanityData to 14 Oct 2026

Discrete Variational Autoencoders

arXiv 1609.02200 ↗First posted 7 Sep 2016stat.ML cs.LGcited by 125

Not on the map. Why?

Abstract (arXiv)

Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete latent variables using the variational autoencoder framework, including backpropagation through the discrete latent variables. The associated class of probabilistic models comprises an undirected discrete component and a directed hierarchical continuous component. The discrete component captures the distribution over the disconnected smooth manifolds induced by the continuous component. As a result, this class of models efficiently learns both the class of objects in an image, and their specific realization in pixels, from unsupervised data, and outperforms state-of-the-art methods on the permutation-invariant MNIST, Omniglot, and Caltech-101 Silhouettes datasets.

Key facts. Cited by 125 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 18; 2022: 30; 2023: 33; 2024: 24; 2025: 10; 2026: 9.

125 papers.

Sort:

By area:

  1. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  2. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  3. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  4. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  5. 2021Score-based Generative Modeling in Latent Spacecited by 636
  6. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  7. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 302
  8. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  9. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  10. 2021PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformerscited by 204
  11. 2021VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modelingcited by 188
  12. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
38 more
  1. 2023TextDiffuser-2: Unleashing the Power of Language Models for Text Renderingcited by 140
  2. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 108
  3. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  4. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  5. 2022MILAN: Masked Image Pretraining on Language Assisted Representationcited by 69
  6. 2022Membership Inference Attacks Against Text-to-image Generation Modelscited by 69
  7. 2022Corrupted Image Modeling for Self-Supervised Visual Pre-Trainingcited by 68
  8. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  9. 2023Hard Patches Mining for Masked Image Modelingcited by 57
  10. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  11. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  12. 2023Event Camera Data Pre-trainingcited by 50
  13. 2022MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformerscited by 47
  14. 2023RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Modelcited by 47
  15. 2023Regularized Vector Quantization for Tokenized Image Synthesiscited by 46
  16. 2022Masked Event Modeling: Self-Supervised Pretraining for Event Camerascited by 41
  17. 2022Recent Advances for Quantum Neural Networks in Generative Learningcited by 39
  18. 2022Self-Guided Diffusion Modelscited by 37
  19. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 35
  20. 2022SIMPLE: A Gradient Estimator for k-Subset Samplingcited by 34
  21. 2023QARV: Quantization-Aware ResNet VAE for Lossy Image Compressioncited by 32
  22. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  23. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  24. 2022Stare at What You See: Masked Image Modeling without Reconstructioncited by 30
  25. 2022Backpropagation through Combinatorial Algorithms: Identity with Projection Workscited by 29
  26. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27
  27. 2021Interpretable agent communication from scratch (with a generic visual processor emerging on the side)cited by 25
  28. 2023Object Discovery from Motion-Guided Tokenscited by 25
  29. 2021Variable-rate discrete representation learningcited by 24
  30. 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
  31. 2024Masked Angle-Aware Autoencoder for Remote Sensing Imagescited by 22
  32. 2024ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretrainingcited by 21
  33. 2020Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitationscited by 20
  34. 2024DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latentscited by 20
  35. 2022Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imaginationcited by 18
  36. 2023ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Datacited by 18
  37. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  38. 2023GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understandingcited by 17

50 most cited of 125 All 125 (JSON)