Pith. sign in

REVIEW 8 cited by

Stabilizing Generative Adversarial Networks: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1910.00927 v2 pith:X6GG264N submitted 2019-09-30 cs.LG

classification cs.LG
keywords generativetrainingadversarialgansmodelnetworksproblemsrecent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative Adversarial Networks (GANs) are a type of generative model which have received much attention due to their ability to model complex real-world data. Despite their recent successes, the process of training GANs remains challenging, suffering from instability problems such as non-convergence, vanishing or exploding gradients, and mode collapse. In recent years, a diverse set of approaches have been proposed which focus on stabilizing the GAN training procedure. The purpose of this survey is to provide a comprehensive overview of the GAN training stabilization methods which can be found in the literature. We discuss the advantages and disadvantages of each approach, offer a comparative summary, and conclude with a discussion of open problems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 65 citations worldwide. Full citation record

  1. RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts

    eess.IV 2025-09 conditional novelty 6.0 of 10

    RoentMod edits chest X-rays to add specific diseases, exposing and partly correcting shortcut learning in AI interpretation models.

  2. Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows

    cs.LG 2025-07 conditional novelty 6.0 of 10

    TarFlowLM models language in a continuous latent space with transformer-based autoregressive normalizing flows, using mixture-CDF and Rosenblatt couplings, and reports competitive NELBO on TEXT8 and OpenWebText.

  3. An Optimisation Framework for Unsupervised Environment Design

    cs.LG 2025-05 conditional novelty 6.0 of 10

    UED is reframed as an entropy-regularized minimax problem with two-timescale gradient convergence guarantees for zero-sum scores, and a generalized learnability score improves robustness on three benchmarks, with the ...

  4. Towards Scalable Topological Regularizers

    cs.LG 2025-01 conditional novelty 6.0 of 10

    Principal persistence measures compared by MMD yield a scalable, GPU-parallel topological regularizer with claimed continuous gradients, improving GAN image generation and semi-supervised classification.

  5. Accelerated Discovery of Vanadium Oxide Compositions: A WGAN-VAE Framework for Materials Design

    cond-mat.mtrl-sci 2025-01 reject novelty 6.0 of 10

    A WGAN-VAE pipeline generates vanadium oxide candidates, reporting 20% stable structures and two V2O3 phases below the Materials Project convex hull, though reference-frame and convergence issues weaken the claim.

  6. CloudBreaker: Breaking the Cloud Covers of Sentinel-2 Images using Multi-Stage Trained Conditional Flow Matching on Sentinel-1

    cs.CV 2025-08 conditional novelty 5.0 of 10

    CloudBreaker trains a multi-stage conditional flow-matching model on paired Sentinel-1 radar and Sentinel-2 optical data to synthesize RGB, NDVI, and NDWI images under cloud cover.

  7. Imputation of Longitudinal Data Using GANs: Challenges and Implications for Classification

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A systematic review of GAN-based longitudinal data imputation that categorizes methods and shows that most ignore missingness mechanisms, static features, and mixed data types.

  8. Towards Digital Twins for Optimal Radioembolization

    eess.IV 2025-08 unverdicted novelty 2.0 of 10

    A review proposing a liver radioembolization digital twin that combines CFD with physics-informed neural networks to plan microsphere delivery.

Pith tools