Adversarially Learned Inference

Abstract

We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space while the inference network maps training examples in data space to the space of latent variables. An adversarial game is cast between these two networks and a discriminative network is trained to distinguish between joint latent/data-space samples from the generative network and joint samples from the inference network. We illustrate the ability of the model to learn mutually coherent inference and generation networks through the inspections of model samples and reconstructions and confirm the usefulness of the learned representations by obtaining a performance competitive with state-of-the-art on the semi-supervised SVHN and CIFAR10 tasks.

References in corpus (26)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• WaveNet: A Generative Model for Raw Audio
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Conditional Image Generation with PixelCNN Decoders
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Pixel Recurrent Neural Networks
• A guide to convolution arithmetic for deep learning
• Theano: new features and speed improvements
• DRAW: A Recurrent Neural Network For Image Generation
• Adversarial Feature Learning
• Autoencoding beyond pixels using a learned similarity metric
• A note on the evaluation of generative models
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Deep Generative Stochastic Networks Trainable by Backprop
• Auxiliary Deep Generative Models
• Neural Photo Editing with Introspective Adversarial Networks
• Stacked What-Where Auto-encoders
• Improving Variational Inference with Inverse Autoregressive Flow
• Generating Images with Perceptual Similarity Metrics based on Deep Networks
• Blocks and Fuel: Frameworks for deep learning
• Is the deconvolution layer the same as a convolutional layer?
• Discriminative Regularization for Generative Models
• Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Form

Cited by in corpus (369)

• Bootstrap your own latent: A new approach to self-supervised Learning
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Generative Adversarial Network in Medical Imaging: A Review
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Training of Wasserstein GANs
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Toward Multimodal Image-to-Image Translation
• Interpolation Consistency Training for Semi-Supervised Learning
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Adversarial Feature Learning
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Deep Clustering for Unsupervised Learning of Visual Features
• Deep Generative Design: Integration of Topology Optimization and Generative Models
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• cGANs with Projection Discriminator
• How Generative Adversarial Networks and Their Variants Work: An Overview
• Learning Graph Embedding with Adversarial Training Methods
• Recent Advances in Autoencoder-Based Representation Learning
• Distribution Matching Losses Can Hallucinate Features in Medical Image Translation
• State Representation Learning for Control: An Overview
• Multimodal Unsupervised Image-to-Image Translation
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• BAGAN: Data Augmentation with Balancing GAN
• Neural Image Compression for Gigapixel Histopathology Image Analysis
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• An Overview of Deep Semi-Supervised Learning
• Mode Regularized Generative Adversarial Networks
• Good Semi-supervised Learning that Requires a Bad GAN
• Triple Generative Adversarial Nets
• Rethinking the Value of Labels for Improving Class-Imbalanced Learning
• Adversarial Text-to-Image Synthesis: A Review
• Optimizing the Latent Space of Generative Networks
• Wasserstein Auto-Encoders
• TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning
• The Numerics of GANs
• Unsupervised Learning via Meta-Learning
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
• Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Do GANs actually learn the distribution? An empirical study
• Deep Generative Dual Memory Network for Continual Learning
• Adversarial Feature Matching for Text Generation
• Dual Discriminator Generative Adversarial Nets
• The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Lifelong Generative Modeling
• BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
• Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
• Boundary-Seeking Generative Adversarial Networks
• A critical analysis of self-supervision, or what we can learn from a single image
• High Fidelity Speech Synthesis with Adversarial Networks
• Adversarial Generation of Natural Language
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Learning Representations for Automatic Colorization
• Connecting Generative Adversarial Networks and Actor-Critic Methods
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Image-to-image translation for cross-domain disentanglement
• Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
• Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
• Triangle Generative Adversarial Networks
• Data Augmentation in Emotion Classification Using Generative Adversarial Networks
• Interpreting the Latent Space of GANs for Semantic Face Editing
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Adversarial Network Embedding
• Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
• Variational Temporal Deep Generative Model for Radar HRRP Target Recognition
• Maximum Entropy Generators for Energy-Based Models
• Implicit Maximum Likelihood Estimation
• Fourier Spectrum Discrepancies in Deep Network Generated Images
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Multi-Generator Generative Adversarial Nets
• Colorization as a Proxy Task for Visual Understanding
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Improved generator objectives for GANs
• Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
• Adversarial Dropout Regularization
• AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
• Defending Model Inversion and Membership Inference Attacks via Prediction Purification
• Time-Contrastive Networks: Self-Supervised Learning from Video
• Activation Maximization Generative Adversarial Nets
• Distribution Matching in Variational Inference
• IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
• Learning Beyond Human Expertise with Generative Models for Dental Restorations
• Prescribed Generative Adversarial Networks
• Stacked Generative Adversarial Networks
• Adversarial Examples - A Complete Characterisation of the Phenomenon
• Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
• A Spectral Approach to Gradient Estimation for Implicit Distributions
• Multi-View Image Generation from a Single-View
• Correction by Projection: Denoising Images with Generative Adversarial Networks
• CR-GAN: Learning Complete Representations for Multi-view Generation
• Adversarially Regularized Autoencoders
• BourGAN: Generative Networks with Metric Embeddings
• Class-Imbalanced Semi-Supervised Learning
• Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
• Adversarial Symmetric Variational Autoencoder
• Approximability of Discriminators Implies Diversity in GANs
• Generative Adversarial Networks for Electronic Health Records: A Framework for Exploring and Evaluating Methods for Predicting Drug-Induced Laboratory Test Trajectories
• Learning Hierarchical Features from Generative Models
• Predicting Deeper into the Future of Semantic Segmentation
• Multi-view Generative Adversarial Networks
• Safer Classification by Synthesis
• Investigating Object Compositionality in Generative Adversarial Networks
• The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
• MGGAN: Solving Mode Collapse using Manifold Guided Training
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• Autoregressive Quantile Networks for Generative Modeling
• Unsupervised Brain Anomaly Detection and Segmentation with Transformers
• Using latent space regression to analyze and leverage compositionality in GANs
• Generative Adversarial Parallelization
• Adversarial score matching and improved sampling for image generation
• Style2Vec: Representation Learning for Fashion Items from Style Sets
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion
• Improved Training of Generative Adversarial Networks Using Representative Features
• GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning
• Unsupervised State Representation Learning in Atari
• Modeling documents with Generative Adversarial Networks
• Structured Generative Adversarial Networks
• Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
• GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
• Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
• Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
• JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
• Semi-supervised Image Attribute Editing using Generative Adversarial Networks
• Inverting The Generator Of A Generative Adversarial Network (II)
• Machine Learning with Membership Privacy using Adversarial Regularization
• Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• Mode Collapse and Regularity of Optimal Transportation Maps
• Learning Clustered Representation for Complex Free Energy Landscapes
• Transferring GANs: generating images from limited data
• Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencoder
• Conditional Image-to-Image Translation
• Wasserstein Dependency Measure for Representation Learning
• Adversarial Message Passing For Graphical Models
• Adversarial Variational Optimization of Non-Differentiable Simulators
• Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
• Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
• Image-to-Image Translation: Methods and Applications
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
• Adversarial Representation Active Learning
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• Message Passing Multi-Agent GANs
• Metropolis-Hastings Generative Adversarial Networks
• xGEMs: Generating Examplars to Explain Black-Box Models
• Hierarchical Adversarially Learned Inference
• Theoretical limitations of Encoder-Decoder GAN architectures
• TorchGAN: A Flexible Framework for GAN Training and Evaluation
• On the Effectiveness of Least Squares Generative Adversarial Networks
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
• Learning to Sketch with Shortcut Cycle Consistency
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• A step towards procedural terrain generation with GANs
• Deep Generative Models for Distribution-Preserving Lossy Compression
• Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
• Effect of The Latent Structure on Clustering with GANs
• Training Invertible Neural Networks as Autoencoders
• Task Specific Adversarial Cost Function
• Active Image Synthesis for Efficient Labeling
• Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
• Learning Occupancy Function from Point Clouds for Surface Reconstruction
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
• Invariant Representations from Adversarially Censored Autoencoders
• Unsupervised learning of object frames by dense equivariant image labelling
• Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
• SGD Learns One-Layer Networks in WGANs
• Image Processing Using Multi-Code GAN Prior
• Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
• Inference in Deep Networks in High Dimensions
• Globally Injective ReLU Networks
• Estimation of Individual Treatment Effect in Latent Confounder Models via Adversarial Learning
• Primal-Dual Wasserstein GAN
• Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
• Gradients as Features for Deep Representation Learning
• RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
• COCO-GAN: Generation by Parts via Conditional Coordinating
• An Introduction to Person Re-identification with Generative Adversarial Networks
• Alleviating Mode Collapse in GAN via Diversity Penalty Module
• Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
• Adversarial Learned Molecular Graph Inference and Generation
• A Brief Introduction to Generative Models
• Variational f-divergence Minimization
• Variational Inference: A Unified Framework of Generative Models and Some Revelations
• Unsupervised Anomaly Detection for X-Ray Images
• EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• Distributional Sliced-Wasserstein and Applications to Generative Modeling
• Triple Generative Adversarial Networks
• C-Learning: Learning to Achieve Goals via Recursive Classification
• An Improved Self-supervised GAN via Adversarial Training
• Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
• 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
• RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• In-Domain GAN Inversion for Real Image Editing
• Wasserstein Variational Inference
• Learning latent representations across multiple data domains using Lifelong VAEGAN
• On the Fairness of Disentangled Representations
• Training Generative Reversible Networks
• Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
• flexgrid2vec: Learning Efficient Visual Representations Vectors
• KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
• Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
• JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels
• Learning Compositional Visual Concepts with Mutual Consistency
• Diverse Image Synthesis from Semantic Layouts via Conditional IMLE
• Image Synthesis From Reconfigurable Layout and Style
• Online Deep Clustering for Unsupervised Representation Learning
• on the effectiveness of generative adversarial network on anomaly detection
• Generative Minimization Networks: Training GANs Without Competition
• Semantic-Aware Generation for Self-Supervised Visual Representation Learning
• DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer
• Generative Models as a Data Source for Multiview Representation Learning
• Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
• Kernel Implicit Variational Inference
• Neural Topic Modeling with Bidirectional Adversarial Training
• Adversarially Approximated Autoencoder for Image Generation and Manipulation
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Multimodal Generative Models for Compositional Representation Learning
• Adversarial Colorization Of Icons Based On Structure And Color Conditions
• Latent Variables on Spheres for Autoencoders in High Dimensions
• Bayesian Conditional Generative Adverserial Networks
• Discriminative-Generative Representation Learning for One-Class Anomaly Detection
• Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
• GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
• AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations
• PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
• Adversarial Graph Disentanglement
• Bidirectional Generative Modeling Using Adversarial Gradient Estimation
• A Plug-in Method for Representation Factorization in Connectionist Models
• Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
• Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
• Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks
• A Simple Framework for Uncertainty in Contrastive Learning
• Generative Hierarchical Features from Synthesizing Images
• Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis
• Active Decision Boundary Annotation with Deep Generative Models
• Deep Generative Learning via Variational Gradient Flow
• To Relieve Your Headache of Training an MRF, Take AdVIL
• Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
• Learning Implicit Generative Models by Teaching Explicit Ones
• DualDis: Dual-Branch Disentangling with Adversarial Learning
• Monocular Real-Time Volumetric Performance Capture
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
• GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
• Robot Learning via Human Adversarial Games
• Decomposed Adversarial Learned Inference
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
• Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization
• Semi-supervised Learning using Adversarial Training with Good and Bad Samples
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• Latent Variable Modeling for Generative Concept Representations and Deep Generative Models
• Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
• Improved BiGAN training with marginal likelihood equalization
• Image-to-Image Translation with Multi-Path Consistency Regularization
• Mode matching in GANs through latent space learning and inversion
• Variational Inference with Holder Bounds
• Cross-Domain Adversarial Auto-Encoder
• Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
• Joint Learning of Generative Translator and Classifier for Visually Similar Classes
• Guided Generative Adversarial Neural Network for Representation Learning and High Fidelity Audio Generation using Fewer Labelled Audio Data
• Reciprocal Adversarial Learning via Characteristic Functions
• InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Adversarially Learned Mixture Model
• How good is my GAN?
• Semi-Implicit Generative Model
• Facial Emotion Recognition with Noisy Multi-task Annotations
• Inferential Wasserstein Generative Adversarial Networks
• Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
• GMM-Based Generative Adversarial Encoder Learning
• Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
• Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
• Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds
• Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
• SaaS: Speed as a Supervisor for Semi-supervised Learning
• Learning Controllable Disentangled Representations with Decorrelation Regularization
• Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss
• DmifNet:3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion
• "Best-of-Many-Samples" Distribution Matching
• Robust GANs against Dishonest Adversaries
• Deconstructing Generative Adversarial Networks
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
• Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• Conditioning Trick for Training Stable GANs
• Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
• Mode Penalty Generative Adversarial Network with adapted Auto-encoder
• Inverse mapping of face GANs
• Generative networks as inverse problems with fractional wavelet scattering networks
• Variation Network: Learning High-level Attributes for Controlled Input Manipulation
• Wasserstein Introspective Neural Networks
• Adversarial Binary Coding for Efficient Person Re-identification
• Hierarchical Video Generation for Complex Data
• Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
• Adaptive Divergence for Rapid Adversarial Optimization
• Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
• IVE-GAN: Invariant Encoding Generative Adversarial Networks
• Signature-Graph Networks
• Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
• KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network
• Non-Asymptotic Error Bounds for Bidirectional GANs
• An Empirical Study of Generative Models with Encoders
• Latent Vector Recovery of Audio GANs
• Traversing Latent Space using Decision Ferns
• Generating new pictures in complex datasets with a simple neural network
• SetGAN: Improving the stability and diversity of generative models through a permutation invariant architecture
• Escaping from Collapsing Modes in a Constrained Space
• Inducing Hierarchical Compositional Model by Sparsifying Generator Network
• Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
• High Diversity Attribute Guided Face Generation with GANs
• Neural Wireframe Renderer: Learning Wireframe to Image Translations
• Towards GANs' Approximation Ability
• On Latent Distributions Without Finite Mean in Generative Models
• Learning to infer in recurrent biological networks
• Forward Amortized Inference for Likelihood-Free Variational Marginalization
• Explorable Tone Mapping Operators
• Modeling Visual Hallucination: A Generative Adversarial Network Framework
• Glioblastoma Multiforme Prognosis: MRI Missing Modality Generation, Segmentation and Radiogenomic Survival Prediction
• IGAN: Inferent and Generative Adversarial Networks
• Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
• MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
• Lifelong Mixture of Variational Autoencoders
• Force-in-domain GAN inversion
• A Survey on Adversarial Image Synthesis
• Dist-GAN: An Improved GAN using Distance Constraints
• Adversarial Stein Training for Graph Energy Models
• AE-StyleGAN: Improved Training of Style-Based Auto-Encoders
• Transductive Adversarial Networks (TAN)
• NeurInt : Learning to Interpolate through Neural ODEs
• Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework
• Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection
• Bayesian Distributional Policy Gradients
• Linear Semantics in Generative Adversarial Networks
• Training Deep Normalizing Flow Models in Highly Incomplete Data Scenarios with Prior Regularization
• Nested Scale Editing for Conditional Image Synthesis
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
• Asymmetric Variational Autoencoders
• Improving Stability of LS-GANs for Audio and Speech Signals
• Evaluating (and improving) the correspondence between deep neural networks and human representations
• Stacked Wasserstein Autoencoder
• Unsupervised Projection Networks for Generative Adversarial Networks
• Learning Improved Representations by Transferring Incomplete Evidence Across Heterogeneous Tasks
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• Adversarial Code Learning for Image Generation
• Generating and Aligning from Data Geometries with Generative Adversarial Networks
• Label-Removed Generative Adversarial Networks Incorporating with K-Means
• Analyzing the benefits of communication channels between deep learning models
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image
• Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation
• Flexible Prior Distributions for Deep Generative Models
• Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions