mlsanityData to 7 Oct 2026

InfoVAE: Information Maximizing Variational Autoencoders

arXiv 1706.02262 ↗First posted 7 Jun 2017cs.LG cs.AI stat.MLcited by 124

Not on the map. Why?

Abstract (arXiv)

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized inference distributions and, in some cases, improving the objective provably degrades the inference quality. In addition, it has been observed that variational autoencoders tend to ignore the latent variables when combined with a decoding distribution that is too flexible. We again identify the cause in existing training criteria and propose a new class of objectives (InfoVAE) that mitigate these problems. We show that our model can significantly improve the quality of the variational posterior and can make effective use of the latent features regardless of the flexibility of the decoding distribution. Through extensive qualitative and quantitative analyses, we demonstrate that our models outperform competing approaches on multiple performance metrics.

Key facts. Cited by 124 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 28; 2023: 22; 2024: 17; 2025: 22; 2026: 10.

124 papers.

Sort:

By area:

  1. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  2. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  3. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  4. 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
  5. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  6. 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
  7. 2023InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Modelscited by 48
  8. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  9. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  10. 2021Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Trackingcited by 35
  11. 2023DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classificationcited by 32
  12. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
38 more
  1. 2023Latent Feature-Guided Diffusion Models for Shadow Removalcited by 28
  2. 2024Diffusion Model with Cross Attention as an Inductive Bias for Disentanglementcited by 27
  3. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  4. 2021Fairness without the sensitive attribute via Causal Variational Autoencodercited by 21
  5. 2022A Differential Entropy Estimator for Training Neural Networkscited by 20
  6. 2021Exploring Autoencoder-based Error-bounded Compression for Scientific Datacited by 19
  7. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  8. 2025Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidancecited by 18
  9. 2021Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reductioncited by 17
  10. 2023Lifting Architectural Constraints of Injective Flowscited by 17
  11. 2021Group Equivariant Subsamplingcited by 15
  12. 2022Interpretable Molecular Graph Generation via Monotonic Constraintscited by 15
  13. 2021Behavior-Driven Synthesis of Human Dynamicscited by 14
  14. 2022Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecastingcited by 14
  15. 2023Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directionscited by 14
  16. 2025Population Aware Diffusion for Time Series Generationcited by 14
  17. 2023GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Modelscited by 13
  18. 2022Disentangled Spatiotemporal Graph Generative Modelscited by 12
  19. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  20. 2023Learning Degradation-Independent Representations for Camera ISP Pipelinescited by 11
  21. 2021Exploring the Latent Space of Autoencoders with Interventional Assayscited by 10
  22. 2022AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modelingcited by 10
  23. 2022Generalization Gap in Amortized Inferencecited by 10
  24. 2024EgoNav: Egocentric Scene-aware Human Trajectory Predictioncited by 9
  25. 2024Regularized Conditional Diffusion Model for Multi-Task Preference Alignmentcited by 9
  26. 2021AI Fairness via Domain Adaptationcited by 8
  27. 2021Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modelingcited by 8
  28. 2022Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulationcited by 8
  29. 2022Towards Effective and Robust Neural Trojan Defenses via Input Filteringcited by 7
  30. 2022Overlooked Implications of the Reconstruction Loss for VAE Disentanglementcited by 7
  31. 2022Forget-me-not! Contrastive Critics for Mitigating Posterior Collapsecited by 6
  32. 2022CustOmics: A versatile deep-learning based strategy for multi-omics integrationcited by 6
  33. 2023InVAErt networks: a data-driven framework for model synthesis and identifiability analysiscited by 6
  34. 2023Data efficient deep learning for medical image analysis: A surveycited by 6
  35. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  36. 2021Disentangling Generative Factors of Physical Fields Using Variational Autoencoderscited by 5
  37. 2022Vitruvio: 3D Building Meshes via Single Perspective Sketchescited by 5
  38. 2023Automatic Generation of Semantic Parts for Face Image Synthesiscited by 5

50 most cited of 124 All 124 (JSON)