Papers › beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

26 Apr 2017ICLR 2017 4archive 2025-07-28

Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner

Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial intelligence that is able to learn and reason in the same way that humans do. We introduce beta-VAE, a new state-of-the-art framework for automated discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner. Our approach is a modification of the variational autoencoder (VAE) framework. We introduce an adjustable hyperparameter beta that balances latent channel capacity and independence constraints with reconstruction accuracy. We demonstrate that beta-VAE with appropriately tuned beta > 1 qualitatively outperforms VAE (beta = 1), as well as state of the art unsupervised (InfoGAN) and semi-supervised (DC-IGN) approaches to disentangled factor learning on a variety of datasets (celebA, faces and chairs). Furthermore, we devise a protocol to quantitatively compare the degree of disentanglement learnt by different models, and show that our approach also significantly outperforms all baselines quantitatively. Unlike InfoGAN, beta-VAE is stable to train, makes few assumptions about the data and relies on tuning a single hyperparameter, which can be directly optimised through a hyper parameter search using weakly labelled data or through heuristic visual inspection for purely unsupervised data.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

AntixK/PyTorch-VAE pytorchApache-2.0Syntology: not harvested report
EugenHotaj/pytorch-generative pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MADE: Masked Autoencoder for Distribution Estimation (arXiv:1502.03509; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified), Neural Autoregressive Distribution Estimation (arXiv:1605.02226; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Conditional Image Generation with PixelCNN Decoders (arXiv:1606.05328; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
adityabingi/Beta-VAE tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Auto-Encoding Variational Bayes (arXiv:1312.6114; that paper's own run record: 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified) and Understanding disentangling in β-VAE (arXiv:1804.03599; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
carbonati/variational-zoo tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Auto-Encoding Variational Bayes (arXiv:1312.6114; that paper's own run record: 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified) and Disentangling by Factorising (arXiv:1802.05983; that paper's own run record: 14 ran (of which 4 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
clementchadebec/benchmark_VAE pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Variational Inference with Normalizing Flows (arXiv:1505.05770; that paper's own run record: 21 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
nmichlo/disent pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Overlooked Implications of the Reconstruction Loss for VAE Disentanglement (arXiv:2202.13341; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Disentanglement

Datasets

Introduced by this paper, per the archive.

dSprites

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Beta-VAE

Beta-VAEDense ConnectionsFeedforward NetworkInfoGANReLUSoftmax

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