Adversarial Feature Learning
arXiv:1605.09782
Abstract
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the data distribution. Intuitively, models trained to predict these semantic latent representations given data may serve as useful feature representations for auxiliary problems where semantics are relevant. However, in their existing form, GANs have no means of learning the inverse mapping -- projecting data back into the latent space. We propose Bidirectional Generative Adversarial Networks (BiGANs) as a means of learning this inverse mapping, and demonstrate that the resulting learned feature representation is useful for auxiliary supervised discrimination tasks, competitive with contemporary approaches to unsupervised and self-supervised feature learning.
arXiv commentPublished as a conference paper at ICLR 2017. Changelog: (v7) Table 2 results improved 1-2% due to averaging predictions over 10 crops at test time, as done in Noroozi & Favaro; Table 3 VOC classification results slightly improved due to minor bugfix. (See v6 changelog for previous versions.)
References in corpus (11)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Sequence to Sequence Learning with Neural Networks
- Caffe: Convolutional Architecture for Fast Feature Embedding
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Adversarially Learned Inference
- Unsupervised Visual Representation Learning by Context Prediction
- Unsupervised Learning of Visual Representations using Videos
- Data-dependent Initializations of Convolutional Neural Networks
- Learning to See by Moving
Cited by in corpus (338)
- Bootstrap your own latent: A new approach to self-supervised Learning
- Generative Adversarial Network in Medical Imaging: A Review
- Unsupervised Representation Learning by Predicting Image Rotations
- NIPS 2016 Tutorial: Generative Adversarial Networks
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Adversarially Learned Inference
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation
- Invertible Conditional GANs for image editing
- 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
- Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
- How Generative Adversarial Networks and Their Variants Work: An Overview
- Recent Advances in Autoencoder-Based Representation Learning
- State Representation Learning for Control: An Overview
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
- Multimodal Unsupervised Image-to-Image Translation
- Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
- Self-supervised learning methods and applications in medical imaging analysis: A survey
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
- BAGAN: Data Augmentation with Balancing GAN
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Neural Photo Editing with Introspective Adversarial Networks
- 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
- Optimizing the Latent Space of Generative Networks
- Learning a Driving Simulator
- Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
- The Numerics of GANs
- Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
- An Introduction to Image Synthesis with Generative Adversarial Nets
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
- Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
- Do GANs actually learn the distribution? An empirical study
- Deep Generative Dual Memory Network for Continual Learning
- Adversarial Feature Matching for Text Generation
- Towards Automated ICD Coding Using Deep Learning
- The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
- The Robust Manifold Defense: Adversarial Training using Generative Models
- Lifelong Generative Modeling
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
- Pretrained Transformers as Universal Computation Engines
- Generative Models for Automatic Chemical Design
- Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
- Hierarchical Implicit Models and Likelihood-Free Variational Inference
- Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
- Learning Representations for Automatic Colorization
- Connecting Generative Adversarial Networks and Actor-Critic Methods
- Precise Recovery of Latent Vectors from Generative Adversarial Networks
- Loss is its own Reward: Self-Supervision for Reinforcement Learning
- Image-to-image translation for cross-domain disentanglement
- Meta-Learning Update Rules for Unsupervised Representation Learning
- Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
- Learning Plannable Representations with Causal InfoGAN
- Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
- Local Aggregation for Unsupervised Learning of Visual Embeddings
- Triangle Generative Adversarial Networks
- Scattering Networks for Hybrid Representation Learning
- Adversarially Regularized Graph Autoencoder for Graph Embedding
- Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN
- Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
- Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
- FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
- Implicit Maximum Likelihood Estimation
- Label Efficient Learning of Transferable Representations across Domains and Tasks
- PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
- Colorization as a Proxy Task for Visual Understanding
- Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
- AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
- Unsupervised Heterogeneous Coupling Learning for Categorical Representation
- Learning Beyond Human Expertise with Generative Models for Dental Restorations
- Prescribed Generative Adversarial Networks
- Adversarial Examples - A Complete Characterisation of the Phenomenon
- 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
- Object Discovery with a Copy-Pasting GAN
- Ensembles of Generative Adversarial Networks
- Look, Listen and Learn
- Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
- BourGAN: Generative Networks with Metric Embeddings
- Adversarially Regularized Autoencoders
- Adversarial Symmetric Variational Autoencoder
- Contrastive Self-supervised Neural Architecture Search
- Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation
- Contrastive Learning with Stronger Augmentations
- Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
- VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detection
- Predicting Deeper into the Future of Semantic Segmentation
- Multi-view Generative Adversarial Networks
- Challenges in Disentangling Independent Factors of Variation
- Safer Classification by Synthesis
- 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
- Quantifying Perceptual Distortion of Adversarial Examples
- Using latent space regression to analyze and leverage compositionality in GANs
- Style2Vec: Representation Learning for Fashion Items from Style Sets
- On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
- Improved Training of Generative Adversarial Networks Using Representative Features
- Colorful Image Colorization
- Modeling documents with Generative Adversarial Networks
- GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
- Structured Generative Adversarial Networks
- Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
- Comparative Study on Generative Adversarial Networks
- Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
- JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
- Inverting The Generator Of A Generative Adversarial Network (II)
- Semi-supervised Image Attribute Editing using Generative Adversarial Networks
- DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks
- Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
- Viewmaker Networks: Learning Views for Unsupervised Representation Learning
- Mode Collapse and Regularity of Optimal Transportation Maps
- Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
- Self-supervised EEG Representation Learning for Automatic Sleep Staging
- Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencoder
- Adversarial Variational Optimization of Non-Differentiable Simulators
- An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
- Wasserstein Dependency Measure for Representation Learning
- Adversarial Message Passing For Graphical Models
- Image-to-Image Translation: Methods and Applications
- Conditional Image-to-Image Translation
- A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
- CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
- Adversarial Representation Active Learning
- Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
- Generative Adversarial Transformers
- xGEMs: Generating Examplars to Explain Black-Box Models
- Hierarchical Adversarially Learned Inference
- Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
- Theoretical limitations of Encoder-Decoder GAN architectures
- Efficient GAN-based method for cyber-intrusion detection
- A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
- O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
- Unsupervised Learning of Video Representations via Dense Trajectory Clustering
- Feature-metric Loss for Self-supervised Learning of Depth and Egomotion
- On the Effectiveness of Least Squares Generative Adversarial Networks
- Deep Generative Models for Distribution-Preserving Lossy Compression
- Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
- Visual Anomaly Detection for Images: A Survey
- Learning to Sketch with Shortcut Cycle Consistency
- A step towards procedural terrain generation with GANs
- Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis
- Associative Compression Networks for Representation Learning
- Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation
- Active Image Synthesis for Efficient Labeling
- Task Specific Adversarial Cost Function
- Effect of The Latent Structure on Clustering with GANs
- Unsupervised learning of object frames by dense equivariant image labelling
- Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
- Invariant Representations from Adversarially Censored Autoencoders
- Estimation of Individual Treatment Effect in Latent Confounder Models via Adversarial Learning
- Gradients as Features for Deep Representation Learning
- Bangla Handwritten Digit Recognition and Generation
- Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
- RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
- Unsupervised learning for concept detection in medical images: a comparative analysis
- Primal-Dual Wasserstein GAN
- Globally Injective ReLU Networks
- SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
- Variational Inference: A Unified Framework of Generative Models and Some Revelations
- Is Discriminator a Good Feature Extractor?
- Understanding the (un)interpretability of natural image distributions using generative models
- Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
- An Introduction to Person Re-identification with Generative Adversarial Networks
- Towards Good Practices in Self-supervised Representation Learning
- Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
- Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
- Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
- Generating Semantic Adversarial Examples via Feature Manipulation
- Variational f-divergence Minimization
- Triple Generative Adversarial Networks
- An Improved Self-supervised GAN via Adversarial Training
- Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
- Self-Supervised Feature Learning by Learning to Spot Artifacts
- Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
- Metropolis-Hastings view on variational inference and adversarial training
- Learning latent representations across multiple data domains using Lifelong VAEGAN
- 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
- Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
- Local Unsupervised Learning for Image Analysis
- Self-Supervised Relative Depth Learning for Urban Scene Understanding
- MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
- Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
- Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
- Diverse Image Synthesis from Semantic Layouts via Conditional IMLE
- on the effectiveness of generative adversarial network on anomaly detection
- When and How Can Deep Generative Models be Inverted?
- Local Label Propagation for Large-Scale Semi-Supervised Learning
- Generative Minimization Networks: Training GANs Without Competition
- Unsupervised MR Motion Artifact Deep Learning using Outlier-Rejecting Bootstrap Aggregation
- Neural Topic Modeling with Bidirectional Adversarial Training
- Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
- Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement
- Adversarial Colorization Of Icons Based On Structure And Color Conditions
- Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
- Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data
- Discriminator Feature-based Inference by Recycling the Discriminator of GANs
- Training VAEs Under Structured Residuals
- Adversarially Approximated Autoencoder for Image Generation and Manipulation
- Kernel Implicit Variational Inference
- Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
- Adversarial Graph Disentanglement
- A Plug-in Method for Representation Factorization in Connectionist Models
- Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
- A Multi-Domain Feature Learning Method for Visual Place Recognition
- Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
- Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
- Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
- Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
- PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
- Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
- Discriminative-Generative Representation Learning for One-Class Anomaly Detection
- AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations
- Unsupervised Transfer Learning with Self-Supervised Remedy
- Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
- Active Decision Boundary Annotation with Deep Generative Models
- Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks
- Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery
- SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis
- In&Out : Diverse Image Outpainting via GAN Inversion
- Disentanglement for Discriminative Visual Recognition
- To Relieve Your Headache of Training an MRF, Take AdVIL
- Deep Self-Supervised Representation Learning for Free-Hand Sketch
- Learning Disentangled Representations of Satellite Image Time Series
- Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization
- Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
- GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
- 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
- Cross-Domain Adversarial Auto-Encoder
- Decomposed Adversarial Learned Inference
- Mode matching in GANs through latent space learning and inversion
- Reciprocal Adversarial Learning via Characteristic Functions
- Neural Topic Modeling with Cycle-Consistent Adversarial Training
- BEHAVE: Behavior-Aware, Intelligent and Fair Resource Management for Heterogeneous Edge-IoT Systems
- Adversarial Pixel-Level Generation of Semantic Images
- Global versus Localized Generative Adversarial Nets
- Image-to-Image Translation with Multi-Path Consistency Regularization
- Double cycle-consistent generative adversarial network for unsupervised conditional generation
- "Best-of-Many-Samples" Distribution Matching
- Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
- Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
- Generative Adversarial Data Programming
- Facial Emotion Recognition with Noisy Multi-task Annotations
- UU-Nets Connecting Discriminator and Generator for Image to Image Translation
- Set Distribution Networks: a Generative Model for Sets of Images
- Unsupervised Image Classification for Deep Representation Learning
- Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss
- Adversarially Learned Mixture Model
- Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation
- Semi-Implicit Generative Model
- MIM: Mutual Information Machine
- DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
- AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
- D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
- Laplacian Denoising Autoencoder
- Conditioning Trick for Training Stable GANs
- Latent Vector Recovery of Audio GANs
- S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
- Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
- Inverse mapping of face GANs
- AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups
- Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning
- Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
- Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
- Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
- Exploring Set Similarity for Dense Self-supervised Representation Learning
- Information Theory-Guided Heuristic Progressive Multi-View Coding
- Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
- Boosting Supervised Learning Performance with Co-training
- Weakly supervised discriminative feature learning with state information for person identification
- Hierarchical Video Generation for Complex Data
- Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks
- Lie Group Auto-Encoder
- Adversarial Binary Coding for Efficient Person Re-identification
- Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation
- Generative Models for Security: Attacks, Defenses, and Opportunities
- Non-Asymptotic Error Bounds for Bidirectional GANs
- Mode Penalty Generative Adversarial Network with adapted Auto-encoder
- Self-supervised Learning with Fully Convolutional Networks
- Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
- Wasserstein Introspective Neural Networks
- Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation
- IVE-GAN: Invariant Encoding Generative Adversarial Networks
- Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
- Deep Learning for Wireless Communications
- Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
- A Classification approach towards Unsupervised Learning of Visual Representations
- Self-supervised Point Set Local Descriptors for Point Cloud Registration
- On Latent Distributions Without Finite Mean in Generative Models
- New Perspective on Progressive GANs Distillation for One-class Novelty Detection
- Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample
- Analyzing the benefits of communication channels between deep learning models
- Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
- Super-Selfish: Self-Supervised Learning on Images with PyTorch
- Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
- Natural Image Manipulation for Autoregressive Models Using Fisher Scores
- Collaboration among Image and Object Level Features for Image Colourisation
- ReshapeGAN: Object Reshaping by Providing A Single Reference Image
- Information based Deep Clustering: An experimental study
- Directional GAN: A Novel Conditioning Strategy for Generative Networks
- Improving Visual Recognition using Ambient Sound for Supervision
- The Implicit Metropolis-Hastings Algorithm
- BooVAE: Boosting Approach for Continual Learning of VAE
- Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features
- Glioblastoma Multiforme Prognosis: MRI Missing Modality Generation, Segmentation and Radiogenomic Survival Prediction
- Escaping from Collapsing Modes in a Constrained Space
- SVMax: A Feature Embedding Regularizer
- Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
- Evaluating (and improving) the correspondence between deep neural networks and human representations
- Improving Stability of LS-GANs for Audio and Speech Signals
- Uncertainty-aware Self-supervised 3D Data Association
- Flexible Prior Distributions for Deep Generative Models
- Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features
- Explorable Tone Mapping Operators
- Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation
- Representation Learning by Reconstructing Neighborhoods
- Learning Rich Representations For Structured Visual Prediction Tasks
- Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
- Traversing Latent Space using Decision Ferns
- Self-Supervised Learning for Large-Scale Unsupervised Image Clustering
- A Survey on Adversarial Image Synthesis
- Multimodal Image Outpainting With Regularized Normalized Diversification
- Force-in-domain GAN inversion
- Unsupervised Projection Networks for Generative Adversarial Networks
- Nested Scale Editing for Conditional Image Synthesis
- Learning to infer in recurrent biological networks
- Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery
- Distributed Anomaly Detection in Edge Streams using Frequency based Sketch Datastructures
- AE-StyleGAN: Improved Training of Style-Based Auto-Encoders
- Dist-GAN: An Improved GAN using Distance Constraints