awesome-DGM-papers
awesome deep generative models papers
https://github.com/liang-hou/awesome-DGM-papers
Last synced: 3 days ago
JSON representation
-
ICLR 2020
-
Poster
- Mixed-curvature Variational Autoencoders - Eugen Ganea, Gary Bécigneul
- AE-OT: A New Generative Model based on Extended Semi-Discrete Optimal Transport - Tung Yau, Xianfeng Gu
- Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models
- VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
- Difference-Seeking Generative Adversarial Network--Unseen Sample Generation - Hsien Hsieh, Soo-Chang Pei, Chun-Shien Lu
- From Variational to Deterministic Autoencoders
- Generative Ratio Matching Networks
- On the "Steerability" of Generative Adversarial Networks
- Semi-Supervised Generative Modeling for Controllable Speech Synthesis - Ryan, Daisy Stanton, David Kao, Tom Bagby
- Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
- Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
- On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
- A Closer Look at the Optimization Landscapes of Generative Adversarial Networks - Julien
- Generative Models for Effective ML on Private, Decentralized Datasets
- Smoothness and Stability in GANs
- Kernel of CycleGAN as a Principal Homogeneous Space
- U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
- Understanding the Limitations of Conditional Generative Models - Henrik Jacobsen, Will Grathwohl, Richard Zemel
- Adversarial Lipschitz Regularization
- Consistency Regularization for Generative Adversarial Networks
- The Shape of Data: Intrinsic Distance for Data Distributions
-
Oral
- Your Classifier is Secretly an Energy based Model and You Should Treat it Like One - Chieh Wang, Joern-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky
- High Fidelity Speech Synthesis with Adversarial Networks
-
Spotlight
-
-
ICML 2021
-
Poster
- Deep Generative Learning via Schrödinger Bridge
- Uncertainty Principles of Encoding GANs - Jun Zha
- Understanding Noise Injection in GANs - Jun Zha
- Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions - Yu Jason Chiang, Vyas Sekar
- Functional Space Analysis of Local GAN Convergence
- Neural SDEs as Infinite-Dimensional GANs
- WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
- On Characterizing GAN Convergence Through Proximal Duality Gap
- Generative Adversarial Transformers
- Provable Lipschitz Certification for Generative Models
- Prior Image-Constrained Reconstruction using Style-Based Generative Models
- NeRF-VAE: A Geometry Aware 3D Scene Generative Model
- Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models
- Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation
- A Language for Counterfactual Generative Models - Lezama
- A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
- Adversarial Purification with Score-based Generative Models
- Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
- Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
- Unified Robust Semi-Supervised Variational Autoencoder
- Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
- MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space
- Autoencoder Image Interpolation by Shaping the Latent Space - Or
- Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
- Autoencoding Under Normalization Constraints - Kyun Noh, Frank Park
- Learning from Nested Data with Ornstein Auto-Encoders - Ho Won
- Monte Carlo Variational Auto-Encoders
- Zero-Shot Text-to-Image Generation
-
-
NeurIPS 2021 ([OpenReview](https://openreview.net/group?id=NeurIPS.cc/2021/Conference))
-
Spotlight
- Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
- Breaking the Dilemma of Medical Image-to-image Translation
- Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency
- On the Value of Infinite Gradients in Variational Autoencoder Models
- Maximum Likelihood Training of Score-Based Diffusion Models
- A Variational Perspective on Diffusion-Based Generative Models and Score Matching - Wei Huang, Jae Hyun Lim, Aaron Courville
- Diffusion Models Beat GANs on Image Synthesis
- Instance-Conditioned GAN
-
Oral
-
Poster
- Self-Supervised GANs with Label Augmentation
- Projected GANs Converge Faster
- Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
- Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis
- Non-asymptotic Error Bounds for Bidirectional GANs
- Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
- CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
- Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
- Particle Cloud Generation with Message Passing Generative Adversarial Networks - roch Vlimant, Dimitrios Gunopulos
- TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
- Low-Rank Subspaces in GANs - Jun Zha, Jingren Zhou, Qifeng Chen
- Lip to Speech Synthesis with Visual Context Attentional GAN
- Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme
- EditGAN: High-Precision Semantic Image Editing
- Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training
- Rethinking Conditional GAN Training: An Approach using Geometrically Structured Latent Manifolds
- BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation
- Data-Efficient Instance Generation from Instance Discrimination
- On the Frequency Bias of Generative Models
- Improved Transformer for High-Resolution GANs
- Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
- Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN
- CogView: Mastering Text-to-Image Generation via Transformers
- Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers
- Manifold Topology Divergence: a Framework for Comparing Data Manifolds
- DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
- A Unified View of cGANs with and without Classifiers - An Chen, Chun-Liang Li, Hsuan-Tien Lin
- Conditional Generation Using Polynomial Expansions
- Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
- Implicit Generative Copulas
- Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction
- Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals
- On the Generative Utility of Cyclic Conditionals - Yan Liu
- Score-based Generative Neural Networks for Large-Scale Optimal Transport
- Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators
- On Memorization in Probabilistic Deep Generative Models
- Score-based Generative Modeling in Latent Space
- SketchGen: Generating Constrained CAD Sketches
- Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
- Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models
- Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
- Improving Robustness using Generated Data - Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy Mann
- D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation
- Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders
- On Density Estimation with Diffusion Models
- Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
- PortaSpeech: Portable and High-Quality Generative Text-to-Speech
- Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models
- Topographic VAEs learn Equivariant Capsules
- ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE
- Understanding Instance-based Interpretability of Variational Auto-Encoders
- Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization
- Consistency Regularization for Variational Auto-Encoders
- Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
-
-
ICML 2020
-
Poster
- Do GANs always have Nash equilibria?
- AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
- SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification
- SGD Learns One-Layer Networks in WGANs
- InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
- Semi-Supervised StyleGAN for Disentanglement Learning
- Implicit competitive regularization in GANs
- Small-GAN: Speeding up GAN Training using Core-Sets
- Bridging the Gap Between f-GANs and Wasserstein GANs
- Reliable Fidelity and Diversity Metrics for Generative Models
- PolyGen: An Autoregressive Generative Model of 3D Meshes
- Implicit Generative Modeling for Efficient Exploration
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
- Understanding and Stabilizing GANs’ Training Dynamics Using Control Theory
- On Leveraging Pretrained GANs for Generation with Limited Data
- Feature Quantization Improves GAN Training
- Invertible generative models for inverse problems: mitigating representation error and dataset bias
- VFlow: More Expressive Generative Flows with Variational Data Augmentation
- Generative Pretraining From Pixels
- Fair Generative Modeling via Weak Supervision
- Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
- Perceptual Generative Autoencoders
- Evaluating Lossy Compression Rates of Deep Generative Models
- Source Separation with Deep Generative Priors
- Distribution Augmentation for Generative Modeling
- On the Power of Compressed Sensing with Generative Models
- Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
- Latent Bernoulli Autoencoder
- Variational Autoencoders with Riemannian Brownian Motion Priors
- Topological Autoencoders
- Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
- ControlVAE: Controllable Variational Autoencoder
- Learning Autoencoders with Relational Regularization
- Learning disconnected manifolds: a no GAN’s land
-
-
NeurIPS 2020
-
Poster
- Teaching a GAN What Not to Learn
- Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
- GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
- Differentiable Augmentation for Data-Efficient GAN Training - Yan Zhu, Song Han
- COT-GAN: Generating Sequential Data via Causal Optimal Transport
- GANSpace: Discovering Interpretable GAN Controls
- Towards a Better Global Loss Landscape of GANs
- Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling - Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio
- GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
- Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN
- Instance Selection for GANs
- Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
- GAN Memory with No Forgetting
- Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data - Jui Hsieh, Yong Jae Lee
- ColdGANs: Taming Language GANs with Cautious Sampling Strategies - Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano
- CircleGAN: Generative Adversarial Learning across Spherical Circles
- ContraGAN: Contrastive Learning for Conditional Image Generation
- Sinkhorn Natural Gradient for Generative Models
- Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance
- Generative View Synthesis: From Single-view Semantics to Novel-view Images
- Training Generative Adversarial Networks by Solving Ordinary Differential Equations
- Woodbury Transformations for Deep Generative Flows
- Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence
- Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation
- A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
- Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining - Lobato
- Training Generative Adversarial Networks with Limited Data
- Improved Techniques for Training Score-Based Generative Models
- Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
- DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
- Efficient Learning of Generative Models via Finite-Difference Score Matching
- GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
- Learning Semantic-aware Normalization for Generative Adversarial Networks - Jun Zha
- Goal-directed Generation of Discrete Structures with Conditional Generative Models
- Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
- Hierarchical Quantized Autoencoders
- Autoregressive Score Matching
- Implicit Rank-Minimizing Autoencoder
- The Autoencoding Variational Autoencoder
- Autoencoders that don't overfit towards the Identity
- NVAE: A Deep Hierarchical Variational Autoencoder
- Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
- Compositional Visual Generation with Energy Based Models
- Strictly Batch Imitation Learning by Energy-based Distribution Matching
- Bi-level Score Matching for Learning Energy-based Latent Variable Models
- Learning Latent Space Energy-Based Prior Model - Chun Zhu, Ying Nian Wu
- A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model
-
-
ICLR 2021
-
Oral
- Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs
- Score-Based Generative Modeling through Stochastic Differential Equations - Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
- Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
- Improved Autoregressive Modeling with Distribution Smoothing
-
Spotlight
- VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
- Large Scale Image Completion via Co-Modulated Generative Adversarial Networks - Chao Chang, Yan Xu
- Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
- A Good Image Generator Is What You Need for High-Resolution Video Synthesis
- GAN "Steerability" without optimization
- Contrastive Divergence Learning is a Time Reversal Adversarial Game
- Influence Estimation for Generative Adversarial Networks
- Distributional Sliced-Wasserstein and Applications to Generative Modeling
- Disentangled Recurrent Wasserstein Autoencoder
- On Self-Supervised Image Representations for GAN Evaluation
-
Poster
- Training GANs with Stronger Augmentations via Contrastive Discriminator
- Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation
- Using latent space regression to analyze and leverage compositionality in GANs
- GANs Can Play Lottery Tickets Too
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation
- Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
- DINO: A Conditional Energy-Based GAN for Domain Translation
- Private Post-GAN Boosting
- GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images
- Taming GANs with Lookahead-Minmax
- Wasserstein-2 Generative Networks
- Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling
- Generative Time-series Modeling with Fourier Flows
- Conditional Generative Modeling via Learning the Latent Space
- not-MIWAE: Deep Generative Modelling with Missing not at Random Data - Alexandre Mattei, Jes Frellsen
- Private Image Reconstruction from System Side Channels Using Generative Models
- Counterfactual Generative Networks
- Learning to Generate 3D Shapes with Generative Cellular Automata
- Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
- Group Equivariant Generative Adversarial Networks
- Refining Deep Generative Models via Discriminator Gradient Flow
- Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
- Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
- Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
- Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
- Understanding Over-parameterization in Generative Adversarial Networks
- Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
- Decentralized Attribution of Generative Models
- Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis - Xiong Wang, Martial Hebert
- A Geometric Analysis of Deep Generative Image Models and Its Applications
- Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
- Property Controllable Variational Autoencoder via Invertible Mutual Dependence
- Anytime Sampling for Autoregressive Models via Ordered Autoencoding
- Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data - Smith
-