pith. sign in

arxiv: 1710.10196 · v3 · submitted 2017-10-27 · 💻 cs.NE · cs.LG· stat.ML

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras , Timo Aila , Samuli Laine , Jaakko Lehtinen This is my paper

Pith reviewed 2026-05-12 12:18 UTC · model grok-4.3

classification 💻 cs.NE cs.LGstat.ML
keywords generative adversarial networksprogressive growinghigh resolution image synthesistraining stabilityimage variationCelebA datasetinception score
0
0 comments X

The pith

Progressive growing of GANs from low to high resolution stabilizes training and yields higher quality images.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a training approach for generative adversarial networks in which the generator and discriminator begin at low resolution and new layers are added progressively to model finer details. This change speeds up the overall process and reduces instability during optimization. The result is the ability to generate images at much higher resolutions with improved visual quality, such as 1024 by 1024 pixels on CelebA, plus higher variation among samples. Additional implementation choices are given to keep the generator and discriminator from falling into destructive patterns.

Core claim

By starting both networks at low resolution and progressively adding layers that capture increasingly fine details, training becomes faster and more stable. This permits generation of 1024 squared CelebA images of high visual quality, an inception score of 8.80 on unsupervised CIFAR-10, and includes several implementation practices that discourage unhealthy generator-discriminator competition, plus a new quality-and-variation metric and an improved CelebA dataset.

What carries the argument

Progressive growing, where new layers are faded in to handle finer image details while preserving previously learned coarse features.

Load-bearing premise

That new layers can be added and faded in without erasing the coarse features already learned at lower resolutions.

What would settle it

Training a standard GAN directly at 1024 by 1024 resolution on CelebA and observing whether it reaches comparable visual quality and training stability without collapse.

read the original abstract

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The paper introduces a progressive growing methodology for training GANs in which both the generator and discriminator begin at low resolution and new layers are incrementally added to model finer details as training proceeds. This is claimed to accelerate training, greatly improve stability, and enable generation of high-quality images at resolutions up to 1024² on CelebA, while also achieving a record unsupervised Inception score of 8.80 on CIFAR-10. Additional contributions include implementation details (equalized learning rates, minibatch discrimination, fade-in blending) to discourage unhealthy generator-discriminator dynamics, a new metric for assessing both image quality and variation, and the release of a higher-quality CelebA dataset.

Significance. If the reported results hold, the work constitutes a substantial practical advance in stabilizing and scaling GAN training for high-resolution synthesis. The empirical evidence—training curves, fade-in ablations, visual results on CelebA and CIFAR-10, and the explicit procedural description of the growth schedule—directly supports the central claims of improved speed, stability, and output quality. The provision of concrete implementation details, the new evaluation metric, and the improved dataset are clear strengths that enhance reproducibility and utility for the community.

minor comments (3)
  1. The abstract states that a 'simple way to increase the variation' is proposed; the main text should supply explicit pseudocode or a numbered algorithmic listing for this component to aid direct implementation.
  2. Figure captions for the high-resolution CelebA samples should explicitly state the exact resolution, number of training iterations, and whether the images are from the final model or an intermediate stage.
  3. A compact table comparing the reported Inception score of 8.80 against the best prior unsupervised results on CIFAR-10 would help readers immediately contextualize the claimed record.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive and accurate summary of our work on progressive growing of GANs. We are pleased that the referee recommends acceptance and agrees that the empirical evidence supports the claims of improved training speed, stability, and image quality.

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper introduces a procedural training methodology for GANs based on progressive resolution growth, with implementation details for layer addition, fade-in, and stabilization techniques. No mathematical derivations, predictions, or first-principles results are claimed that could reduce to inputs by construction. All central claims (improved quality, stability, variation) rest on experimental outcomes such as training curves, ablation studies, and metrics on external datasets like CelebA and CIFAR10, which serve as independent validation rather than tautological reductions. No self-citations exist as load-bearing elements since this is the original work, and no ansatzes or uniqueness theorems are invoked in a self-referential manner.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 0 invented entities

This is an empirical methods paper; the central claim rests on the assumption that progressive layer addition stabilizes adversarial dynamics. Free parameters include the exact growth schedule, fade-in rates, and standard GAN hyperparameters tuned experimentally. No new physical or mathematical entities are postulated.

free parameters (2)
  • progressive growth schedule and fade-in parameters
    The resolution steps and transition durations are chosen experimentally to maintain stability.
  • GAN training hyperparameters (learning rates, batch sizes, etc.)
    Standard hyperparameters are tuned specifically for the progressive regime.
axioms (1)
  • domain assumption Starting at low resolution and progressively adding layers stabilizes GAN training without catastrophic interference with prior features
    Invoked to justify the core methodology; supported only by the reported experiments.

pith-pipeline@v0.9.0 · 5454 in / 1350 out tokens · 46782 ms · 2026-05-12T12:18:49.348295+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 60 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Generative Language Modeling for Automated Theorem Proving

    cs.LG 2020-09 unverdicted novelty 8.0

    GPT-f, a transformer-based prover for Metamath, generated new short proofs that were accepted into the main library—the first such contribution from a deep-learning system.

  2. AI safety via debate

    stat.ML 2018-05 conditional novelty 8.0

    AI agents trained through competitive debate can allow polynomial-time human judges to oversee PSPACE-level questions, with MNIST experiments boosting sparse classifier accuracy from 59% to 89% using only 6 pixels.

  3. Training-Free Generative Sampling via Moment-Matched Score Smoothing

    stat.ML 2026-05 unverdicted novelty 7.0

    MM-SOLD is a training-free particle sampler whose large-particle limit converges to a moment-matched Gibbs distribution obtained by exponentially tilting a score-smoothed target.

  4. ImageAttributionBench: How Far Are We from Generalizable Attribution?

    cs.CV 2026-05 unverdicted novelty 7.0

    ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.

  5. What Cohort INRs Encode and Where to Freeze Them

    cs.LG 2026-05 unverdicted novelty 7.0

    Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.

  6. LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    LEGO uses multiple generator-specific LoRA modules modulated by an MLP and fused with attention to detect synthetic images, achieving better performance than prior methods while using under 10% of the training data.

  7. Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges

    cs.LG 2026-05 unverdicted novelty 7.0

    Structured diffusion bridges with alignment constraints achieve near fully-paired quality in modality translation while working effectively in unpaired and semi-paired regimes.

  8. ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation

    cs.CV 2026-04 unverdicted novelty 7.0

    A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.

  9. ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis

    cs.CV 2026-04 unverdicted novelty 7.0

    ReImagine decouples human appearance from temporal consistency via pretrained image backbones, SMPL-X motion guidance, and training-free video diffusion refinement to generate high-quality controllable videos.

  10. MetaCloak-JPEG: JPEG-Robust Adversarial Perturbation for Preventing Unauthorized DreamBooth-Based Deepfake Generation

    cs.CV 2026-04 unverdicted novelty 7.0

    MetaCloak-JPEG uses a DiffJPEG layer with straight-through estimator inside a JPEG-aware EOT and curriculum meta-learning loop to produce l-inf bounded perturbations that retain 91.3% effectiveness after real JPEG com...

  11. ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

    cs.CV 2026-04 unverdicted novelty 7.0

    ExpertEdit edits novice motions to expert skill levels by learning a motion prior from unpaired videos and infilling masked skill-critical spans.

  12. LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction

    cs.CV 2026-03 conditional novelty 7.0

    LPNSR derives optimal intermediate noise for diffusion SR via MLE and implements it with an LR-guided noise predictor, reaching SOTA perceptual quality in 4 steps without text priors.

  13. From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

    cs.LG 2026-03 unverdicted novelty 7.0

    Transport-geodesic attribution via optimal generative flows selects principled paths for feature attributions by minimizing kinetic action.

  14. Factored Classifier-Free Guidance

    cs.CV 2025-06 unverdicted novelty 7.0

    Factored Classifier-Free Guidance enables per-attribute control in classifier-free guidance for diffusion models to produce more sound counterfactuals.

  15. Toward Generalizable Forgery Detection and Reasoning

    cs.CV 2025-03 unverdicted novelty 7.0

    FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.

  16. Diffusion Posterior Sampling for General Noisy Inverse Problems

    stat.ML 2022-09 unverdicted novelty 7.0

    Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.

  17. High-Resolution Image Synthesis with Latent Diffusion Models

    cs.CV 2021-12 conditional novelty 7.0

    Latent diffusion models achieve state-of-the-art inpainting and competitive results on unconditional generation, scene synthesis, and super-resolution by performing the diffusion process in the latent space of pretrai...

  18. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

    cs.CV 2021-08 conditional novelty 7.0

    SDEdit performs guided image synthesis and editing by adding noise to inputs and refining them via denoising with a diffusion model's SDE prior, outperforming GAN methods in human studies without task-specific training.

  19. Guided Image Generation with Conditional Invertible Neural Networks

    cs.CV 2019-07 unverdicted novelty 7.0

    Proposes cINN architecture for conditional image generation that by construction yields diverse sharp samples, demonstrated on MNIST digit generation and image colorization with latent space manipulation.

  20. Controlla: Learning Controllability via Graph-Constrained Latent Geometry

    cs.CV 2026-05 unverdicted novelty 6.0

    Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport to enforce consistent attribute trajectories while preserving referenc...

  21. Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

    cs.CV 2026-05 conditional novelty 6.0

    SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.

  22. The Diffusion Encoder

    cs.LG 2026-05 unverdicted novelty 6.0

    A diffusion model serves as the encoder in an autoencoder when trained alternately with the decoder to resolve opposing update directions while retaining the standard diffusion training objective.

  23. Deep Probabilistic Unfolding for Quantized Compressive Sensing

    cs.CV 2026-05 unverdicted novelty 6.0

    A probabilistic unfolding network with stable likelihood projection and dual-domain Mamba achieves state-of-the-art reconstruction in quantized compressive sensing.

  24. DiffATS: Diffusion in Aligned Tensor Space

    cs.LG 2026-05 unverdicted novelty 6.0

    DiffATS trains diffusion models directly on aligned Tucker tensor primitives that are proven to be homeomorphisms, delivering efficient unconditional and conditional generation across images, videos, and PDE data with...

  25. Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    ODP-Net uses instance-aware orthogonal decomposition, perturbation-based purification, and manifold alignment to separate universal forgery traces, generator fingerprints, and semantics, achieving SOTA on unseen archi...

  26. Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    ODP-Net structurally disentangles universal forgery traces from generator fingerprints and semantics via orthogonal decomposition and purification, delivering state-of-the-art generalization to unseen AI image generat...

  27. Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees

    cs.LG 2026-05 unverdicted novelty 6.0

    Error in approximating the tangent conditional score by the unconditional score in diffusion models is bounded by dimension-free conditional mutual information, with a projected-Langevin method outperforming baselines...

  28. A Few-Step Generative Model on Cumulative Flow Maps

    cs.LG 2026-05 unverdicted novelty 6.0

    Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.

  29. Which Face and Whose Identity? Solving the Dual Challenge of Deepfake Proactive Forensics in Multi-Face Scenarios

    cs.CV 2026-04 unverdicted novelty 6.0

    DAWF embeds identity watermarks via a parallel multi-face architecture and uses selective loss to answer which face was forged and whose identity was used.

  30. Selective Depthwise Separable Convolution for Lightweight Joint Source-Channel Coding in Wireless Image Transmission

    eess.IV 2026-04 unverdicted novelty 6.0

    A selective replacement of convolutional layers by depthwise separable convolutions in JSCC systems cuts parameters substantially while keeping reconstruction performance nearly intact for wireless image transmission.

  31. Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection

    cs.CV 2026-04 unverdicted novelty 6.0

    MAFL uses adversarial training to suppress pattern and content biases, guiding models to learn shared generative features for better cross-model generalization in detecting AI images.

  32. SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    SyncBreaker jointly attacks image and audio streams with Multi-Interval Sampling and Cross-Attention Fooling to degrade speech-driven talking head generation more than single-modality baselines.

  33. Mitigating Membership Inference in Intermediate Representations with Differentially Private Training

    cs.LG 2026-02 unverdicted novelty 6.0

    LM-DP-SGD estimates layer-specific MIA risks from shadow models and reweights gradients to give stronger protection to vulnerable layers, improving the privacy-utility trade-off over uniform DP-SGD.

  34. CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness

    cs.CV 2026-02 unverdicted novelty 6.0

    CASR enables stable arbitrary-scale super-resolution by breaking extreme magnifications into cyclic in-distribution transitions with SSAM for structural distribution alignment and SARM for texture self-similarity pres...

  35. Implicit Neural Representation-Based Continuous Single Image Super-Resolution: An Empirical Benchmark

    cs.CV 2026-01 unverdicted novelty 6.0

    Systematic benchmark reveals recent complex INR methods for continuous image super-resolution offer only marginal gains, with performance tied to training setups, auxiliary losses improving textures, and scaling laws holding.

  36. Open Set Face Forgery Detection via Dual-Level Evidence Collection

    cs.CV 2025-12 unverdicted novelty 6.0

    DLED reformulates open-set face forgery detection as an uncertainty estimation task and uses dual-level spatial-frequency evidence collection to identify novel fake categories, claiming 20% average gains over baselines.

  37. Training-Free Reward-Guided Image Editing via Trajectory Optimal Control

    cs.CV 2025-09 unverdicted novelty 6.0

    A trajectory optimal control framework for reward-guided image editing in diffusion models that balances reward maximization with source fidelity better than prior inversion-based baselines.

  38. DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation

    cs.CV 2025-07 unverdicted novelty 6.0

    DiffClean applies text-guided diffusion to erase makeup from faces, boosting age estimation and verification accuracy over makeup-affected images.

  39. Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?

    cs.CV 2025-07 conditional novelty 6.0

    The ITW-SM dataset and targeted optimization of detector design choices yield a 26.87% average AUC improvement for state-of-the-art AI-generated image detectors under real-world social media conditions.

  40. NullFace: Training-Free Localized Face Anonymization

    cs.CV 2025-03 unverdicted novelty 6.0

    NullFace performs training-free localized face anonymization by inverting images to noise and denoising with modified identity embeddings from a pre-trained diffusion model.

  41. VideoGPT: Video Generation using VQ-VAE and Transformers

    cs.CV 2021-04 accept novelty 6.0

    VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.

  42. Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning

    cs.CV 2026-05 unverdicted novelty 5.0

    EMSFD uses Dirichlet-based evidence modeling to capture prediction uncertainty in synthetic face detection and applies uncertainty-driven active learning to achieve 15% higher accuracy than prior methods.

  43. Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning

    cs.CV 2026-05 unverdicted novelty 5.0

    EMSFD models synthetic face detection via Dirichlet evidence and uncertainty-driven active learning, reporting 15% higher accuracy than prior state-of-the-art methods while improving reliability on out-of-distribution images.

  44. Exploring and Exploiting Stability in Latent Flow Matching

    cs.LG 2026-05 unverdicted novelty 5.0

    Latent Flow Matching models exhibit inherent stability to data reduction and model shrinkage due to the flow matching objective, enabling reduced-dataset training and two-stage inference with over 2x speedup while pre...

  45. Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges

    cs.LG 2026-05 unverdicted novelty 5.0

    A structured diffusion bridge method achieves near fully-paired modality translation quality using alignment constraints even in unpaired or semi-paired regimes.

  46. Mesh Based Simulations with Spatial and Temporal awareness

    cs.LG 2026-05 unverdicted novelty 5.0

    A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention corre...

  47. IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations

    cs.CV 2026-05 unverdicted novelty 5.0

    IdentiFace is a multi-modal iterative diffusion framework that generates identifiable suspect faces with improved identity retrieval for law enforcement applications.

  48. HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detection

    cs.CV 2026-04 unverdicted novelty 5.0

    HiMix combines mixup augmentation to create transitional real-fake samples with hierarchical global-local artifact feature fusion to achieve better generalization in detecting AI-generated images from unseen generators.

  49. The Amazing Stability of Flow Matching

    cs.CV 2026-04 unverdicted novelty 5.0

    Flow matching generative models preserve sample quality, diversity, and latent representations despite pruning 50% of the CelebA-HQ dataset or altering architecture and training configurations.

  50. DiffMagicFace: Identity Consistent Facial Editing of Real Videos

    cs.CV 2026-04 unverdicted novelty 5.0

    DiffMagicFace uses concurrent fine-tuned text and image diffusion models plus a rendered multi-view dataset to achieve identity-consistent text-conditioned editing of real facial videos.

  51. Quantum generative modeling for financial time series with temporal correlations

    quant-ph 2025-07 unverdicted novelty 5.0

    QGANs with quantum generators and classical discriminators generate financial time series matching target distributions and desired temporal correlations, with quality varying by circuit depth, bond dimension, and sim...

  52. Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme

    cs.LG 2025-05 unverdicted novelty 5.0

    AEQ-RVAE-ST combines approximate equivariance and progressive sequence lengthening in a recurrent VAE to match or exceed prior generative models on quasi-periodic time series benchmarks.

  53. PortraVec: Image-Based Portrait Vectorization with Text-Guided Manipulation

    cs.CV 2024-10 unverdicted novelty 5.0

    PortraVec converts portrait images to vector sketches via attention-aware offset sampling for structure and region-based parameter freezing for text-guided local edits, claiming better consistency and controllability ...

  54. Justifying Diagnosis Decisions by Deep Neural Networks

    cs.LG 2019-07 unverdicted novelty 5.0

    A multi-task deep learning model maps frontal X-rays to continuous text for producing diagnoses, textual justifications, and alternative images, with expert study showing better justification than saliency maps.

  55. EPNAS: Efficient Progressive Neural Architecture Search

    cs.LG 2019-07 unverdicted novelty 5.0

    EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNe...

  56. Cellular State Transformations using Generative Adversarial Networks

    q-bio.QM 2019-06 unverdicted novelty 5.0

    TSPG applies conditional GANs to generate realistic transcriptome perturbations that mimic source-to-target gene expression state transitions and highlight biologically enriched genes.

  57. Adaptive Forensic Feature Refinement via Intrinsic Importance Perception

    cs.CV 2026-04 unverdicted novelty 4.0

    I2P adaptively selects the most discriminative layers from visual foundation models for synthetic image detection and constrains task updates to low-sensitivity parameter subspaces to improve specificity without harmi...

  58. Deepfakes: we need to re-think the concept of "real" images

    cs.CV 2025-09 unverdicted novelty 4.0

    This position paper contends that the concept of 'real' images must be rethought because most modern photographs are computationally generated, undermining current deepfake detection methods.

  59. Why Build an Assistant in Minecraft?

    cs.AI 2019-07 unverdicted novelty 4.0

    A rationale is presented for developing an assistant in Minecraft to advance natural language understanding and dialogue learning.

  60. Topology Maintained Structure Encoding

    cs.CV 2019-06 unverdicted novelty 3.0

    CSVD Voronoi encoder proposed to maintain topology for improved contour extraction in CNNs and structure generation in GANs.

Reference graph

Works this paper leans on

58 extracted references · 58 canonical work pages · cited by 58 Pith papers · 5 internal anchors

  1. [1]

    Towards principled methods for training generative adversarial networks

    Martin Arjovsky and L\' e on Bottou. Towards principled methods for training generative adversarial networks. In ICLR, 2017

    work page 2017

  2. [2]

    Wasserstein GAN

    Martin Arjovsky, Soumith Chintala, and L\' e on Bottou. Wasserstein GAN . CoRR, abs/1701.07875, 2017

    work page Pith review arXiv 2017

  3. [3]

    Do GANs actually learn the distribution? An empirical study

    Sanjeev Arora and Yi Zhang. Do GAN s actually learn the distribution? an empirical study. CoRR, abs/1706.08224, 2017

    work page Pith review arXiv 2017

  4. [4]

    Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. Layer normalization. CoRR, abs/1607.06450, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  5. [5]

    Greedy layer-wise training of deep networks

    Yoshua Bengio, Pascal Lamblin, Dan Popovici, and Hugo Larochelle. Greedy layer-wise training of deep networks. In P. B. Sch\" o lkopf, J. C. Platt, and T. Hoffman (eds.), NIPS, pp.\ 153--160. 2007

    work page 2007

  6. [6]

    BEGAN: Boundary Equilibrium Generative Adversarial Networks

    David Berthelot, Tom Schumm, and Luke Metz. BEGAN: B oundary equilibrium generative adversarial networks. CoRR, abs/1703.10717, 2017

    work page Pith review arXiv 2017

  7. [7]

    Burt and Edward H

    Peter J. Burt and Edward H. Adelson. Readings in computer vision: Issues, problems, principles, and paradigms. chapter The Laplacian Pyramid As a Compact Image Code, pp.\ 671--679. 1987

    work page 1987

  8. [8]

    Photographic image synthesis with cascaded refinement networks

    Qifeng Chen and Vladlen Koltun. Photographic image synthesis with cascaded refinement networks. CoRR, abs/1707.09405, 2017

    work page arXiv 2017

  9. [9]

    Hovy, and Aaron C

    Zihang Dai, Amjad Almahairi, Philip Bachman, Eduard H. Hovy, and Aaron C. Courville. Calibrating energy-based generative adversarial networks. In ICLR, 2017

    work page 2017

  10. [10]

    Deep generative image models using a laplacian pyramid of adversarial networks

    Emily L. Denton, Soumith Chintala, Arthur Szlam, and Robert Fergus. Deep generative image models using a L aplacian pyramid of adversarial networks. CoRR, abs/1506.05751, 2015

    work page arXiv 2015

  11. [11]

    Adversarially Learned Inference

    Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Alex Lamb, Martin Arjovsky, Olivier Mastropietro, and Aaron Courville. Adversarially learned inference. CoRR, abs/1606.00704, 2016

    work page Pith review arXiv 2016

  12. [12]

    Durugkar, Ian Gemp, and Sridhar Mahadevan

    Ishan P. Durugkar, Ian Gemp, and Sridhar Mahadevan. Generative multi-adversarial networks. CoRR, abs/1611.01673, 2016

    work page arXiv 2016

  13. [13]

    A growing neural gas network learns topologies

    Bernd Fritzke. A growing neural gas network learns topologies. In G. Tesauro, D. S. Touretzky, and T. K. Leen (eds.), Advances in Neural Information Processing Systems 7, pp.\ 625--632. 1995

    work page 1995

  14. [14]

    Namboodiri, Philip H

    Arnab Ghosh, Viveka Kulharia, Vinay P. Namboodiri, Philip H. S. Torr, and Puneet Kumar Dokania. Multi-agent diverse generative adversarial networks. CoRR, abs/1704.02906, 2017

    work page arXiv 2017

  15. [15]

    Generative Adversarial Networks

    Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative Adversarial Networks . In NIPS, 2014

    work page 2014

  16. [16]

    Class-Splitting Generative Adversarial Networks

    Guillermo L. Grinblat, Lucas C. Uzal, and Pablo M. Granitto. Class-splitting generative adversarial networks. CoRR, abs/1709.07359, 2017

    work page Pith review arXiv 2017

  17. [17]

    Improved Training of Wasserstein GANs

    Ishaan Gulrajani, Faruk Ahmed, Mart \' n Arjovsky, Vincent Dumoulin, and Aaron C. Courville. Improved training of W asserstein GAN s. CoRR, abs/1704.00028, 2017

    work page Pith review arXiv 2017

  18. [18]

    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. CoRR, abs/1502.01852, 2015

    work page Pith review arXiv 2015

  19. [19]

    GANs trained by a two time-scale update rule converge to a local Nash equilibrium

    Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In NIPS, pp.\ 6626--6637. 2017

    work page 2017

  20. [20]

    Boundary-Seeking Generative Adversarial Networks

    R Devon Hjelm, Athul Paul Jacob, Tong Che, Kyunghyun Cho, and Yoshua Bengio. Boundary-Seeking Generative Adversarial Networks . CoRR, abs/1702.08431, 2017

    work page arXiv 2017

  21. [21]

    Stacked Generative Adversarial Networks

    Xun Huang, Yixuan Li, Omid Poursaeed, John E. Hopcroft, and Serge J. Belongie. Stacked generative adversarial networks. CoRR, abs/1612.04357, 2016

    work page Pith review arXiv 2016

  22. [22]

    Globally and locally consistent image completion

    Satoshi Iizuka, Edgar Simo-Serra, and Hiroshi Ishikawa. Globally and locally consistent image completion. ACM Trans. Graph., 36 0 (4): 0 107:1--107:14, 2017

    work page 2017

  23. [23]

    Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

    Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. CoRR, abs/1502.03167, 2015

    work page internal anchor Pith review arXiv 2015

  24. [24]

    Kingma and Jimmy Ba

    Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015

    work page 2015

  25. [25]

    Kingma and Max Welling

    Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. In ICLR, 2014

    work page 2014

  26. [26]

    Improved variational inference with inverse autoregressive flow

    Diederik P Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, and Max Welling. Improved variational inference with inverse autoregressive flow. In NIPS, volume 29, pp.\ 4743--4751. 2016

    work page 2016

  27. [27]

    On Convergence and Stability of GANs

    Naveen Kodali, Jacob D. Abernethy, James Hays, and Zsolt Kira. How to train your DRAGAN . CoRR, abs/1705.07215, 2017

    work page Pith review arXiv 2017

  28. [28]

    Single image super-resolution using deep learning, 2017

    Dmitry Korobchenko and Marco Foco. Single image super-resolution using deep learning, 2017. URL https://gwmt.nvidia.com/super-res/about. Machines Can See summit

    work page 2017

  29. [29]

    Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pp.\ 1097--1105. 2012

    work page 2012

  30. [30]

    Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

    Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew P. Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. Photo-realistic single image super-resolution using a generative adversarial network. CoRR, abs/1609.04802, 2016

    work page Pith review arXiv 2016

  31. [31]

    PacGAN: The power of two samples in generative adversarial networks

    Zinan Lin, Ashish Khetan, Giulia Fanti, and Sewoong Oh. PacGAN: The power of two samples in generative adversarial networks . CoRR, abs/1712.04086, 2017

    work page arXiv 2017

  32. [32]

    Unsupervised image-to-image translation networks

    Ming - Yu Liu, Thomas Breuel, and Jan Kautz. Unsupervised image-to-image translation networks. CoRR, abs/1703.00848, 2017

    work page arXiv 2017

  33. [33]

    Deep learning face attributes in the wild

    Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In ICCV, 2015

    work page 2015

  34. [34]

    Alireza Makhzani and Brendan J. Frey. Pixel GAN autoencoders. CoRR, abs/1706.00531, 2017

    work page arXiv 2017

  35. [35]

    Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

    Xiao - Jiao Mao, Chunhua Shen, and Yu - Bin Yang. Image restoration using convolutional auto-encoders with symmetric skip connections. CoRR, abs/1606.08921, 2016 a

    work page Pith review arXiv 2016

  36. [36]

    Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, and Zhen Wang. Least squares generative adversarial networks. CoRR, abs/1611.04076, 2016 b

    work page Pith review arXiv 2016

  37. [37]

    Megapixel size image creation using generative adversarial networks

    Marco Marchesi. Megapixel size image creation using generative adversarial networks. CoRR, abs/1706.00082, 2017

    work page arXiv 2017

  38. [38]

    Unrolled generative adversarial networks

    Luke Metz, Ben Poole, David Pfau, and Jascha Sohl - Dickstein. Unrolled generative adversarial networks. CoRR, abs/1611.02163, 2016

    work page arXiv 2016

  39. [39]

    Conditional image synthesis with auxiliary classifier GAN s

    Augustus Odena, Christopher Olah, and Jonathon Shlens. Conditional image synthesis with auxiliary classifier GAN s. In ICML, 2017

    work page 2017

  40. [40]

    Wasserstein barycenter and its application to texture mixing

    Julien Rabin, Gabriel Peyr�, Julie Delon, and Marc Bernot. Wasserstein barycenter and its application to texture mixing. In Scale Space and Variational Methods in Computer Vision (SSVM), pp.\ 435--446, 2011

    work page 2011

  41. [41]

    Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

    Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. CoRR, abs/1511.06434, 2015

    work page internal anchor Pith review arXiv 2015

  42. [42]

    Tim Salimans and Diederik P. Kingma. Weight normalization: A simple reparameterization to accelerate training of deep neural networks. CoRR, abs/1602.07868, 2016

    work page Pith review arXiv 2016

  43. [43]

    Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen

    Tim Salimans, Ian J. Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. Improved techniques for training GAN s. In NIPS, 2016

    work page 2016

  44. [44]

    Stanley and Risto Miikkulainen

    Kenneth O. Stanley and Risto Miikkulainen. Evolving neural networks through augmenting topologies. Evolutionary Computation, 10 0 (2): 0 99--127, 2002

    work page 2002

  45. [45]

    Tijmen Tieleman and Geoffrey E. Hinton. Lecture 6.5 - RMSProp . Technical report, COURSERA: Neural Networks for Machine Learning, 2012

    work page 2012

  46. [46]

    Lempitsky

    Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. Adversarial generator-encoder networks. CoRR, abs/1704.02304, 2017

    work page arXiv 2017

  47. [47]

    WaveNet: A Generative Model for Raw Audio

    A \" a ron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew W. Senior, and Koray Kavukcuoglu. WaveNet: A generative model for raw audio. CoRR, abs/1609.03499, 2016 a

    work page internal anchor Pith review arXiv 2016

  48. [48]

    Pixel recurrent neural networks

    A\" a ron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. Pixel recurrent neural networks. In ICML, pp.\ 1747--1756, 2016 b

    work page 2016

  49. [49]

    Conditional Image Generation with PixelCNN Decoders

    A \" a ron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, and Koray Kavukcuoglu. Conditional image generation with PixelCNN decoders. CoRR, abs/1606.05328, 2016 c

    work page Pith review arXiv 2016

  50. [50]

    L2 Regularization versus Batch and Weight Normalization

    Twan van Laarhoven. L2 regularization versus batch and weight normalization. CoRR, abs/1706.05350, 2017

    work page Pith review arXiv 2017

  51. [51]

    High-resolution image synthesis and semantic manipulation with conditional GANs

    Ting - Chun Wang, Ming - Yu Liu, Jun - Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. High-resolution image synthesis and semantic manipulation with conditional GANs . CoRR, abs/1711.11585, 2017

    work page arXiv 2017

  52. [52]

    Simoncelli, and Alan C

    Zhou Wang, Eero P. Simoncelli, and Alan C. Bovik. Multi-scale structural similarity for image quality assessment. In Proc. IEEE Asilomar Conf. on Signals, Systems, and Computers, pp.\ 1398--1402, 2003

    work page 2003

  53. [53]

    Improving generative adversarial networks with denoising feature matching

    David Warde-Farley and Yoshua Bengio. Improving generative adversarial networks with denoising feature matching. In ICLR, 2017

    work page 2017

  54. [54]

    LR-GAN: layered recursive generative adversarial networks for image generation

    Jianwei Yang, Anitha Kannan, Dhruv Batra, and Devi Parikh. LR-GAN: layered recursive generative adversarial networks for image generation. In ICLR, 2017

    work page 2017

  55. [55]

    LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

    Fisher Yu, Yinda Zhang, Shuran Song, Ari Seff, and Jianxiong Xiao. LSUN: C onstruction of a large-scale image dataset using deep learning with humans in the loop. CoRR, abs/1506.03365, 2015

    work page internal anchor Pith review arXiv 2015

  56. [56]

    Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaolei Huang, Xiaogang Wang, and Dimitris N. Metaxas. StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV, 2017

    work page 2017

  57. [57]

    Energy-based generative adversarial network

    Junbo Jake Zhao, Micha \" e l Mathieu, and Yann LeCun. Energy-based generative adversarial network. In ICLR, 2017

    work page 2017

  58. [58]

    Jun - Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. CoRR, abs/1703.10593, 2017

    work page arXiv 2017