paper-with-me

Papers

Neural Discrete Representation Learning

2017-11-02 · NeurIPS 2017 12 · Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), 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, we incorporate ideas from vector quantisation (VQ). 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, providing further evidence of the utility of the learnt representations.

📄 PDF Abstract BibTeX arXiv:1711.00937

Code (50)

deepmind/sonnet/blob/v2/sonnet/src/nets/vqvae.py 공식 구현 tf
AntixK/PyTorch-VAE pytorch
AnzorGozalishvili/autoencoders_playground
EugenHotaj/pytorch-generative/blob/master/pytorch_generative/models/vae/vq_vae.py pytorch
Geson-anko/VQ_AutoEncoder pytorch
HenningBuhl/VQ-VAE_Keras_Implementation tf
MishaLaskin/vq-vae pytorch
MishaLaskin/vqvae pytorch
R4j4n/Vector-Quantized-Variational-Autoencoders-VQ-VAE- pytorch
StanislavParovoy/VQ-VAE-WaveNet tf
airalcorn2/vqvae-pytorch pytorch
andrecianflone/vector_quantization pytorch
archinetai/bitcodes-pytorch pytorch
artem-gorodetskii/wikiart-latent-diffusion pytorch
awei669/VQ-Font pytorch
bshall/VectorQuantizedCPC pytorch
bshall/ZeroSpeech pytorch
buaavrcg/LEGaussians pytorch
clementchadebec/benchmark_VAE pytorch
dhgrs/chainer-VQ-VAE
explainingai-code/VQVAE-Pytorch pytorch
hiwonjoon/tf-vqvae tf
inzva/music-generation
iomanker/VQVAE-TF2 tf
jackson-kang/pytorch-vae-tutorial pytorch
jaywalnut310/Vector-Quantized-Autoencoders tf
joh-fischer/PlantLDM pytorch
karpathy/deep-vector-quantization pytorch
keras-team/keras-io/blob/master/examples/generative/vq_vae.py tf
ks2labs/modules pytorch
lucidrains/vector-quantize-pytorch pytorch
lupalab/posterior-matching jax
nadavbh12/VQ-VAE pytorch
nicolaffETHZ/Brain2Word_paper tf
opendrivelab/univla pytorch
rhoposit/icassp2021 pytorch
rsn870/VQ-VAE pytorch
safakkbilici/Synthetic-Music-Generation-with-Deep-Neural-Networks
sarus-tech/tf2-published-models/tree/master/vqvae tf
sisl/MultiAgentVariationalOcclusionInference pytorch
swasun/VQ-VAE-Speech pytorch
swasun/VQ-VAE-images pytorch
unixpickle/vq-draw pytorch
v-iashin/SpecVQGAN pytorch
vignesh-creator/VectorQuantized-VAE pytorch
wayexists02/vqvae-pytorch-impl pytorch
yashgarg98/VQ-VAE
yhy258/VariationalAutoEncoders-Pytorch pytorch
yjlolo/vae-audio pytorch
zer0sh0t/artificial_intelligence/tree/master/autoencoders/vector_quantized_variational_ae pytorch

Tasks

DecoderRepresentation Learning

Methods 이 논문이 사용한 방법론

Dilated Causal Convolution A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by…
Adam 설명 없음
Batch Normalization 설명 없음
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
VQ-VAE VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It differs from…

Similar Papers 제목 키워드 기반

Autoregressive Co-Training for Learning Discrete Speech Representations

2022-03-29 · Sung-Lin Yeh, Hao Tang

While several self-supervised approaches for learning discrete speech representation have been proposed, it is unclear how these seemingly similar approaches relate to each other. In this paper, we consider a generative …

Quantization

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

2026-03-19 · Yuqing Wang, Chuofan Ma, Zhijie Lin, Yao Teng 외 arxiv

Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal architectures. However, current discret…

Offline RL with Discrete Proxy Representations for Generalizability in POMDPs

2023-09-21 · NeurIPS 2023 11

Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, …

Is Information in the Brain Represented in Continuous or Discrete Form?

2020-09-16

The question of continuous-versus-discrete information representation in the brain is a fundamental yet unresolved question. Historically, most analyses assume a continuous representation without considering the discrete…

Form

Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification

2020-04-28 · Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen

Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the di…

General Classificationtext-classificationText ClassificationUnsupervised Text Classification