Papers of the day   All papers

Generating Diverse High-Fidelity Images with VQ-VAE-2


Jun 04 2019 Aäron van den Oord

VQVAE-2 finally out! Powerful autoregressive models in a hierarchical compressed latent space. No modes were collapsed in the creation of these samples ;) Arixv: With @catamorphist and @vinyals More samples and details 👇 [thread]
12 replies, 896 likes

Jun 04 2019 Oriol Vinyals

Surprising how simple ideas can yield such a good generative model! -Mean Squared Error loss on pixels -Non-autoregressive image decoder -Discrete latents w/ straight through estimator w/ @catamorphist & @avdnoord VQ-VAE-2: Code:
7 replies, 662 likes

Jun 28 2019 Oriol Vinyals

Great post by Prof. David McAllester on why discrete representations matter, based on our findings in VQ-VAE2. "Vector quantization seems to be a minimal-bias way for symbols to enter into deep models."
4 replies, 406 likes

Jun 04 2019 Ben Poole

Big hierarchical VQ-VAEs with autoregressive priors do amazing things. Awesome work from @catamorphist @avdnoord @OriolVinyalsML:
2 replies, 324 likes

Jun 04 2019 roadrunner01

Generating Diverse High-Fidelity Images with VQ-VAE-2 pdf: abs:
2 replies, 127 likes

Jun 04 2019 Gene Kogan

For most of the creatives/non-scientists out there, this may seem like just another BigGAN/StyleGAN, but this has important advantages: It's likelihood-based (can be evaluated formally), samples much faster, and should be superior in generator diversity. Really good stuff
3 replies, 113 likes

Jun 04 2019 Xander Steenbrugge

Generative Modelling space on fire! After Google's #BigGan and Nvidia's #StyleGAN we now finally have autoencoder based models that generate samples of equal/better? quality! The sample diversity is especially striking given that mode collapse has always been an issue for GANs.
0 replies, 51 likes

Jun 04 2019 Kyle McDonald

VAE-style networks have surpassed the quality of BigGAN and StyleGAN. i always knew they had it in them 🎉
1 replies, 43 likes

Jun 04 2019 Max Jaderberg

Insanely good samples from the latest incarnation of the VQVAE generative model
1 replies, 40 likes

Jun 06 2019 François Fleuret

Beside the quantitative evidences that they are more robust to mode collapse than GANs, their roots in "classical" density estimation make VAE more promising as a generic tool. We have "good enough classifiers" since 2015, maybe are we also good for density models...
0 replies, 27 likes

Jun 04 2019 Danilo J. Rezende

Great results on generative modelling from @catamorphist, @avdnoord and @OriolVinyalsML !
0 replies, 21 likes

Jun 04 2019 Daisuke Okanohara

VQ-VAE-2 improves VQ-VAE by using1) hierarchical latent variables 2) a prior distribution that matches the marginal posterior using an auto-regressive model with self-attention; achieving diverse and high-fidelity image generation.
0 replies, 15 likes

Jun 04 2019 d00d

VAE based image generation with quality comparable to GAN generated images, but more variety and faster sampling...
1 replies, 12 likes

Jun 04 2019 Kaixhin

I love this mix between very general (autoregressively-decoded discrete sequences), general (hierarchical structure) and specific (local spatial structure) priors to model complex distributions in the real world 🌏
0 replies, 6 likes

Jun 18 2019 Alex Nichol

The VQ-VAE-2 paper is hilariously vague. E.g. "It consists of a few residual blocks followed by a number of strided transposed convolutions". (Paper:
1 replies, 6 likes

Jul 29 2019 René Schulte

Impressive new step for generated images. The below photos are all synthesized by an AI 👌 Instead of a GAN they use a Vector Quantized Variational AutoEncoder (VQ-VAE) which makes it easier to handle and much faster. 🚀 #AI #DeepLearning #ML #DNN
0 replies, 6 likes

Sep 30 2019 Alex J. Champandard

2/ At this stage, we know it's possible to generate HD images with many/most techniques. NVIDIA built StyleGAN, OpenAI developed GLOW, DeepMind created VQVAE, etc. Everyone has their favorite! 🐕 .
1 replies, 4 likes

Sep 30 2019 Alex J. Champandard

6/ The idea of working in a smaller and coarser space is not new. It's what made GANs scale to 1024x1024 in the first place (progressive growing) and it's the idea that helped VQVAE catch up.
1 replies, 3 likes

Jun 05 2019 Kyle Kastner

@selimonder This paper (along with a few others recently such as , are exploiting the multi-scale structure inherent in audio and images. That kind of structure is much harder to get *easily* in language - dependency which may not be local
1 replies, 2 likes

Jul 01 2019 Seth Stafford

THIS: "The . shift from symbolic logic . to distributed vector representations is . viewed as [a] cornerstone of . deep learning . I . believe . logical symbolic reasoning is necessary for AGI. Vector quantization seems . a minimal-bias way for symbols to enter . deep models."
0 replies, 1 likes