Methods › Computer Vision › Likelihood-Based Generative Models › VQ-VAE

VQ-VAE

197 papers tagged archive 2025-07-28

Introduced by Aaron van den Oord et al. in Neural Discrete Representation Learning

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, ideas from vector quantisation (VQ) are incorporated. Using the VQ method allows the model to circumvent issues of posterior collapse - where the latents are ignored when they are paired with a powerful autoregressive decoder - typically observed in the VAE framework. Pairing these representations with an autoregressive prior, the model can generate high quality images, videos, and speech as well as doing high quality speaker conversion and unsupervised learning of phonemes.

PaperSource

Papers archive 2025-07-28

30 shown of 197, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 171 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Quantization30
Decoder28
Image Generation23
Representation Learning17
Motion Generation13
Language Modelling12
Motion Synthesis11
Image Reconstruction10
Language Modeling10
Speech Synthesis10
Disentanglement7
Video Generation7
Clustering6
Denoising6
Diversity6
Music Generation6
Text-to-Image Generation6
Transfer Learning6
Large Language Model5
Self-Supervised Learning5

Usage over time archive 2025-07-28

Papers per year tagged with VQ-VAE: 2017 to 2025, peak 46 46 0 2017: 1 paper 2017 2018: 2 papers 2018 2019: 6 papers 2019 2020: 19 papers 2020 2021: 29 papers 2021 2022: 31 papers 2022 2023: 46 papers 2023 2024: 41 papers 2024 2025: 22 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (197 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Likelihood-Based Generative ModelsGenerative Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections