mlsanityData to 14 Oct 2026

Hierarchical Quantized Autoencoders

arXiv 2002.08111 ↗First posted 19 Feb 2020cs.LG cs.CV cs.NEcited by 57

Not on the map. Why?

Abstract (arXiv)

Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning discrete representations with Vector Quantized Variational Autoencoders (VQ-VAEs), we motivate the use of a hierarchy of VQ-VAEs to attain high factors of compression. We show that the combination of stochastic quantization and hierarchical latent structure aids likelihood-based image compression. This leads us to introduce a novel objective for training hierarchical VQ-VAEs. Our resulting scheme produces a Markovian series of latent variables that reconstruct images of high-perceptual quality which retain semantically meaningful features. We provide qualitative and quantitative evaluations on the CelebA and MNIST datasets.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 17; 2024: 11; 2025: 14; 2026: 7.

57 papers.

Sort:

By area:

  1. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  2. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 440
  3. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 117
  4. 2023Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networkscited by 82
  5. 2024Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%cited by 68
  6. 2023Online Clustered Codebookcited by 55
  7. 2021Soft then Hard: Rethinking the Quantization in Neural Image Compressioncited by 51
  8. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 41
  9. 2023DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusioncited by 37
  10. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 35
  11. 2023QARV: Quantization-Aware ResNet VAE for Lossy Image Compressioncited by 32
  12. 2024T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Textcited by 30
38 more
  1. 2023HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayescited by 27
  2. 2022Hierarchical Sketch Induction for Paraphrase Generationcited by 22
  3. 2023Vector Quantized Wasserstein Auto-Encodercited by 22
  4. 2023EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoderscited by 16
  5. 2024Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modelingcited by 16
  6. 2024Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learningcited by 11
  7. 2023StraIT: Non-autoregressive Generation with Stratified Image Transformercited by 10
  8. 2023T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representationscited by 10
  9. 2021Hierarchical disentangled representation learning for singing voice conversioncited by 9
  10. 2025Discrete Tokenization for Multimodal LLMs: A Comprehensive Surveycited by 8
  11. 2025GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domaincited by 7
  12. 2022Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generationcited by 6
  13. 2024MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wildcited by 5
  14. 2025Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Studycited by 5
  15. 2025MoSa: Motion Generation with Scalable Autoregressive Modelingcited by 5
  16. 2022Semantic Image Synthesis with Semantically Coupled VQ-Modelcited by 4
  17. 2023Tokenization with Factorized Subword Encodingcited by 4
  18. 2023LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representationscited by 4
  19. 2025Virtual Full-stack Scanning of Brain MRI via Imputing Any Quantised Codecited by 4
  20. 2024Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Modelscited by 3
  21. 2024CigTime: Corrective Instruction Generation Through Inverse Motion Editingcited by 3
  22. 2025MSDformer: Multi-scale Discrete Transformer For Time Series Generationcited by 3
  23. 2023MEMORY-VQ: Compression for Tractable Internet-Scale Memorycited by 2
  24. 2023Discrete Distribution Networkscited by 2
  25. 2024Gaussian Mixture Vector Quantization with Aggregated Categorical Posteriorcited by 2
  26. 2025Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learningcited by 2
  27. 2025Exploiting Discriminative Codebook Prior for Autoregressive Image Generationcited by 2
  28. 2025MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matchingcited by 2
  29. 2021Learned transform compression with optimized entropy encodingcited by 1
  30. 2022Multiresolution Signal Processing of Financial Market Objectscited by 1
  31. 2024Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformerscited by 1
  32. 2026Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Frameworkcited by 1
  33. 2023MAGMA: Music Aligned Generative Motion Autodecodercited by 0
  34. 2024Deep-Learned Compression for Radio-Frequency Signal Classificationcited by 0
  35. 2025Dual Codebook VQ: Enhanced Image Reconstruction with Reduced Codebook Sizecited by 0
  36. 2025POET: Prompt Offset Tuning for Continual Human Action Adaptationcited by 0
  37. 2025BiomechGPT: Extending Motion-Language Models to Clinical Motion Understandingcited by 0
  38. 2025Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variablescited by 0

50 most cited of 57 All 57 (JSON)