Methods › Computer Vision › Generative Adversarial Networks › InfoGAN
InfoGAN
Introduced by Xi Chen et al. in InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
InfoGAN is a type of generative adversarial network that modifies the GAN objective to encourage it to learn interpretable and meaningful representations. This is done by maximizing the mutual information between a fixed small subset of the GAN’s noise variables and the observations.
Formally, InfoGAN is defined as a minimax game with a variational regularization of mutual information and the hyperparameter λ:
min_(G, Q)max_DV_(INFOGAN)(D, G, Q) = V(D, G) - λL_I(G, Q)
Where Q is an auxiliary distribution that approximates the posterior P(c|x) - the probability of the latent code c given the data x - and L_I is the variational lower bound of the mutual information between the latent code and the observations.
In the practical implementation, there is another fully-connected layer to output parameters for the conditional distribution Q (negligible computation ontop of regular GAN structures). Q is represented with a softmax non-linearity for a categorical latent code. For a continuous latent code, the authors assume a factored Gaussian.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1606.03657'). Repositories: 38 listed of 38 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1606.03657, not a method entry. This answer is about arXiv:1606.03657, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1606.03657 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 35 · with a code link: 14 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 35 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 35 of 35, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Generative Adversarial Networks Bridging Art and Machine Intelligence 6 Feb 2025 · 0 repositories · arXiv:2502.04116
-
Unsupervised and Interpretable Synthesizing for Electrical Time Series Based on Information Maximizing Generative Adversarial Nets 18 Jul 2024 · 0 repositories · arXiv:2407.13691
-
Comparing the information content of probabilistic representation spaces 31 May 2024 · 1 repository · arXiv:2405.21042
-
Double InfoGAN for Contrastive Analysis 31 Jan 2024 · 1 repository · arXiv:2401.17776
-
GAN-GA: A Generative Model based on Genetic Algorithm for Medical Image Generation 30 Dec 2023 · 0 repositories · arXiv:2401.00314
-
Fusing Conditional Submodular GAN and Programmatic Weak Supervision 16 Dec 2023 · 1 repository · arXiv:2312.10366Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
The objective function equality property of infoGAN for two-layer network 30 Sep 2023 · 0 repositories · arXiv:2310.00443
-
HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information 6 Aug 2022 · 1 repository · arXiv:2208.03563
-
k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension 17 Jun 2022 · 0 repositories · arXiv:2206.08526
-
Analytical Interpretation of Latent Codes in InfoGAN with SAR Images 26 May 2022 · 0 repositories · arXiv:2205.13294
-
LatentGAN Autoencoder: Learning Disentangled Latent Distribution 5 Apr 2022 · 0 repositories · arXiv:2204.02010
-
Contrastive Fine-grained Class Clustering via Generative Adversarial Networks 30 Dec 2021 · 1 repository · arXiv:2112.14971Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey 26 Nov 2021 · 0 repositories · arXiv:2111.13282
-
Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion 2 Oct 2021 · 0 repositories · arXiv:2110.00788
-
ADIS-GAN: Affine Disentangled GAN 1 Jan 2021 · 0 repositories
-
Representation Decomposition for Image Manipulation and Beyond 2 Nov 2020 · 0 repositories · arXiv:2011.00788
-
DPD-InfoGAN: Differentially Private Distributed InfoGAN 22 Oct 2020 · 0 repositories · arXiv:2010.11398
-
CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks 4 Jun 2020 · 1 repository · arXiv:2006.02951
-
Disentanglement based Active Learning 15 Dec 2019 · 1 repository · arXiv:1912.07018
-
Towards Better Understanding of Disentangled Representations via Mutual Information 25 Nov 2019 · 0 repositories · arXiv:1911.10922
-
Generative Adversarial Networks for Failure Prediction 4 Oct 2019 · 0 repositories · arXiv:1910.02034
-
Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data 1 Oct 2019 · 1 repository · arXiv:1910.01112
-
Generating Geological Facies Models with Fidelity to Diversity and Statistics of Training Images using Improved Generative Adversarial Networks 23 Sep 2019 · 0 repositories · arXiv:1909.10652
-
Maximizing Mutual Information for Tacotron 30 Aug 2019 · 2 repositories · arXiv:1909.01145
-
Unsupervised Classification of Street Architectures Based on InfoGAN 30 May 2019 · 0 repositories · arXiv:1905.12844
-
Learning Robotic Manipulation through Visual Planning and Acting 11 May 2019 · 0 repositories · arXiv:1905.04411
-
IB-GAN: Disentangled Representation Learning with Information Bottleneck GAN 1 May 2019 · 2 repositories
-
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs 20 Apr 2019 · 1 repository · arXiv:1904.09507
-
Heartbeat Anomaly Detection using Adversarial Oversampling 28 Jan 2019 · 1 repository · arXiv:1901.09972
-
Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning 26 Jan 2018 · 0 repositories · arXiv:1801.08712
-
The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling 1 Jan 2018 · 0 repositories
-
Towards Grounding Conceptual Spaces in Neural Representations 15 Jun 2017 · 0 repositories · arXiv:1706.04825
-
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework 26 Apr 2017 · 6 repositories
-
Image Generation and Editing with Variational Info Generative AdversarialNetworks 17 Jan 2017 · 0 repositories · arXiv:1701.04568
-
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets 12 Jun 2016 · 38 repositories · arXiv:1606.03657Syntology 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
Tasks archive 2025-07-28
20 shown of 50 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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