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

Abstract

While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required to optimize millions of parameters in deep network models. Lagging behind the growth in model capacity, the available datasets are quickly becoming outdated in terms of size and density. To circumvent this bottleneck, we propose to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop. Starting from a large set of candidate images for each category, we iteratively sample a subset, ask people to label them, classify the others with a trained model, split the set into positives, negatives, and unlabeled based on the classification confidence, and then iterate with the unlabeled set. To assess the effectiveness of this cascading procedure and enable further progress in visual recognition research, we construct a new image dataset, LSUN. It contains around one million labeled images for each of 10 scene categories and 20 object categories. We experiment with training popular convolutional networks and find that they achieve substantial performance gains when trained on this dataset.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Going Deeper with Convolutions
• Deep Image: Scaling up Image Recognition

Cited by in corpus (368)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Denoising Diffusion Probabilistic Models
• Improved Training of Wasserstein GANs
• Score-Based Generative Modeling through Stochastic Differential Equations
• Learning from Synthetic Humans
• Energy-based Generative Adversarial Network
• Density estimation using Real NVP
• A Survey of Human-in-the-loop for Machine Learning
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Generating Natural Adversarial Examples
• Energy-based Out-of-distribution Detection
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Understanding the Role of Individual Units in a Deep Neural Network
• InfoVAE: Information Maximizing Variational Autoencoders
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Predictive Uncertainty Estimation via Prior Networks
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
• Guided Image Generation with Conditional Invertible Neural Networks
• Identification of Deep Network Generated Images Using Disparities in Color Components
• Leveraging Frequency Analysis for Deep Fake Image Recognition
• Stabilizing Training of Generative Adversarial Networks through Regularization
• BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Glow: Generative Flow with Invertible 1x1 Convolutions
• L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
• Demystifying MMD GANs
• An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
• Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks
• Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Least Squares Generative Adversarial Networks
• Swapping Autoencoder for Deep Image Manipulation
• Improved Techniques for Training Score-Based Generative Models
• AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
• Vision-based Real Estate Price Estimation
• Algorithmic decision-making in AVs: Understanding ethical and technical concerns for smart cities
• Do GANs actually learn the distribution? An empirical study
• Accelerating 3D Deep Learning with PyTorch3D
• Generative Visual Manipulation on the Natural Image Manifold
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• Super-Resolution via Deep Learning
• BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
• Diffusion Model-Based Image Editing: A Survey
• Outlier Exposure with Confidence Control for Out-of-Distribution Detection
• Synthetic Humans for Action Recognition from Unseen Viewpoints
• ViTGAN: Training GANs with Vision Transformers
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Generic 3D Representation via Pose Estimation and Matching
• A Review of Deep Learning-based Approaches for Deepfake Content Detection
• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
• Deep Learning for Image Super-resolution: A Survey
• On Self Modulation for Generative Adversarial Networks
• Generative Steganography Network
• A Study of Face Obfuscation in ImageNet
• Appropriateness of Performance Indices for Imbalanced Data Classification: An Analysis
• Metric Learning for Novelty and Anomaly Detection
• Memory Replay GANs: learning to generate images from new categories without forgetting
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Closed-Form Factorization of Latent Semantics in GANs
• Reliable Fidelity and Diversity Metrics for Generative Models
• On Fast Sampling of Diffusion Probabilistic Models
• Few-Shot Adaptation of Generative Adversarial Networks
• Multi-Generator Generative Adversarial Nets
• Collective Decision of One-vs-Rest Networks for Open Set Recognition
• ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Facial-Sketch Synthesis: A New Challenge
• CNN-generated images are surprisingly easy to spot... for now
• Revisiting Video Saliency: A Large-scale Benchmark and a New Model
• Why is the Mahalanobis Distance Effective for Anomaly Detection?
• Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
• A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA
• StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
• ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning
• An Improved Evaluation Framework for Generative Adversarial Networks
• Convolution with even-sized kernels and symmetric padding
• Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
• A Convex Duality Framework for GANs
• Noise Estimation for Generative Diffusion Models
• On the Importance of Gradients for Detecting Distributional Shifts in the Wild
• Conditional Gaussian Distribution Learning for Open Set Recognition
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
• CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise
• Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Online Continual Learning on Sequences
• 3D Hand Shape and Pose Estimation from a Single RGB Image
• Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
• Small-GAN: Speeding Up GAN Training Using Core-sets
• Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• Robust Out-of-distribution Detection for Neural Networks
• Adversarial Learning with Local Coordinate Coding
• A Large-Scale Study on Regularization and Normalization in GANs
• AIBench: An Industry Standard Internet Service AI Benchmark Suite
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
• Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
• Forensic Analysis of Synthetically Generated Western Blot Images
• Simple yet Effective Way for Improving the Performance of GAN
• Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
• Adversarial score matching and improved sampling for image generation
• BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite
• Improved Training of Generative Adversarial Networks Using Representative Features
• Dense outlier detection and open-set recognition based on training with noisy negative images
• Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers
• Scribbler: Controlling Deep Image Synthesis with Sketch and Color
• McGan: Mean and Covariance Feature Matching GAN
• Out-of-Distribution Detection using Multiple Semantic Label Representations
• Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
• OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
• Wavelet Transform-assisted Adaptive Generative Modeling for Colorization
• Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• Deep CNN-based Multi-task Learning for Open-Set Recognition
• Towards Open-World Text-Guided Face Image Generation and Manipulation
• Transferring GANs: generating images from limited data
• Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
• Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
• Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
• Unsupervised Diverse Colorization via Generative Adversarial Networks
• Latent Convolutional Models
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• A Survey on Deep Generative 3D-aware Image Synthesis
• Wavelet Flow: Fast Training of High Resolution Normalizing Flows
• Gotta Go Fast When Generating Data with Score-Based Models
• Mimicry: Towards the Reproducibility of GAN Research
• Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
• Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• Learning Human Optical Flow
• Regression Prior Networks
• Non Gaussian Denoising Diffusion Models
• Adversarial Defense by Latent Style Transformations
• Generative Adversarial Transformers
• Finding Mixed Nash Equilibria of Generative Adversarial Networks
• Integrating GAN and Texture Synthesis for Enhanced Road Damage Detection
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses
• Flat2Layout: Flat Representation for Estimating Layout of General Room Types
• Image Generation From Small Datasets via Batch Statistics Adaptation
• Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
• Few-shot Image Generation via Cross-domain Correspondence
• DOOM Level Generation using Generative Adversarial Networks
• Learning Energy-Based Models by Diffusion Recovery Likelihood
• Deep Generative Models for Distribution-Preserving Lossy Compression
• SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending
• Emergence of Object Segmentation in Perturbed Generative Models
• RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis
• Learning-based Defect Recognition for Quasi-Periodic Microscope Images
• Understanding Open-Set Recognition by Jacobian Norm and Inter-Class Separation
• SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• A Variational Dirichlet Framework for Out-of-Distribution Detection
• Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
• Novelty Detection Via Blurring
• Building robust classifiers through generation of confident out of distribution examples
• Scalable Deep Learning Logo Detection
• Heatmap-based Out-of-Distribution Detection
• Controllable Generative Adversarial Network
• Image Processing Using Multi-Code GAN Prior
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
• On the Units of GANs (Extended Abstract)
• Generative Convolution Layer for Image Generation
• Few-shot Image Generation via Masked Discrimination
• Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
• cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL
• Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
• Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs
• A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
• COCO-GAN: Generation by Parts via Conditional Coordinating
• ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
• Optimal transport maps for distribution preserving operations on latent spaces of Generative Models
• Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning
• M2IOSR: Maximal Mutual Information Open Set Recognition
• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• Source Separation with Deep Generative Priors
• Annealing Genetic GAN for Minority Oversampling
• Open Set Recognition with Conditional Probabilistic Generative Models
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
• Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
• DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer
• Fine-grained Synthesis of Unrestricted Adversarial Examples
• Editing in Style: Uncovering the Local Semantics of GANs
• Deep TEN: Texture Encoding Network
• Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
• Interface Design for Crowdsourcing Hierarchical Multi-Label Text Annotations
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
• Generating Images with Sparse Representations
• Self-Supervised GAN to Counter Forgetting
• HyperInverter: Improving StyleGAN Inversion via Hypernetwork
• Learning Diverse Image Colorization
• RPGAN: GANs Interpretability via Random Routing
• One-Shot Generative Domain Adaptation
• In-Domain GAN Inversion for Real Image Editing
• Group Equivariant Generative Adversarial Networks
• Detecting OODs as datapoints with High Uncertainty
• No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
• Anycost GANs for Interactive Image Synthesis and Editing
• ExSinGAN: Learning an Explainable Generative Model from a Single Image
• Generative networks as inverse problems with Scattering transforms
• Positional Encoding as Spatial Inductive Bias in GANs
• Self Sparse Generative Adversarial Networks
• Probing the Purview of Neural Networks via Gradient Analysis
• Multimodal Group Emotion Recognition In-the-wild Using Privacy-Compliant Features
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• Multiscale Score Matching for Out-of-Distribution Detection
• Unsupervised Joint Mining of Deep Features and Image Labels for Large-scale Radiology Image Categorization and Scene Recognition
• Self-Supervised GANs via Auxiliary Rotation Loss
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• Sharkzor: Interactive Deep Learning for Image Triage, Sort and Summary
• Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning
• FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
• DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
• Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
• Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
• Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks
• Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
• SNIPS: Solving Noisy Inverse Problems Stochastically
• cGANs with Conditional Convolution Layer
• TwoStreamVAN: Improving Motion Modeling in Video Generation
• Training VAEs Under Structured Residuals
• CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network
• Galaxy Imaging with Generative Models: Insights from a Two-Models Framework
• An Acceleration Framework for High Resolution Image Synthesis
• Improving generative adversarial network inversion via fine-tuning GAN encoders
• MaCow: Masked Convolutional Generative Flow
• KIT MOMA: A Mobile Machines Dataset
• Joint Intensity-Gradient Guided Generative Modeling for Colorization
• Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation
• Variance Regularizing Adversarial Learning
• First Order Generative Adversarial Networks
• GAN Cocktail: mixing GANs without dataset access
• On Noise Injection in Generative Adversarial Networks
• A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers
• Model Extraction and Defenses on Generative Adversarial Networks
• NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
• Unsupervised multi-modal Styled Content Generation
• Generalized Energy Based Models
• An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
• In&Out : Diverse Image Outpainting via GAN Inversion
• Training Deep Neural Network in Limited Precision
• Fast Inference in Denoising Diffusion Models via MMD Finetuning
• A Simple Framework for Uncertainty in Contrastive Learning
• PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
• Random mesh projectors for inverse problems
• GIQA: Generated Image Quality Assessment
• Provably Robust Detection of Out-of-distribution Data (almost) for free
• Generative Hierarchical Features from Synthesizing Images
• Adversarial Attacks on Co-Occurrence Features for GAN Detection
• VOMTC: Vision Objects for Millimeter and Terahertz Communications
• Improving the Performance of Fine-Grain Image Classifiers via Generative Data Augmentation
• Generative Adversarial Mapping Networks
• Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction
• PriorGAN: Real Data Prior for Generative Adversarial Nets
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering
• Low Distortion Block-Resampling with Spatially Stochastic Networks
• BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
• AIBench Training: Balanced Industry-Standard AI Training Benchmarking
• Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval
• GAN Memory with No Forgetting
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Training Generative Adversarial Networks in One Stage
• CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models
• Unifying Heterogeneous Classifiers with Distillation
• Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space
• Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss
• Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
• Object-Level Context Modeling For Scene Classification with Context-CNN
• Toward Joint Image Generation and Compression using Generative Adversarial Networks
• Prior Networks for Detection of Adversarial Attacks
• An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks
• Reciprocal Adversarial Learning via Characteristic Functions
• Secure Data Sharing With Flow Model
• Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data
• Content-Aware Preserving Image Generation
• Thinkback: Task-SpecificOut-of-Distribution Detection
• GAN Inversion for Out-of-Range Images with Geometric Transformations
• Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection
• Auditing AI models for Verified Deployment under Semantic Specifications
• Dual Contradistinctive Generative Autoencoder
• Gradient Origin Networks
• Weakly supervised training of deep convolutional neural networks for overhead pedestrian localization in depth fields
• Bridging In- and Out-of-distribution Samples for Their Better Discriminability
• Sliced Wasserstein Generative Models
• Channel-Recurrent Autoencoding for Image Modeling
• Exploring The Effect of High-frequency Components in GANs Training
• Hierarchical approach to classify food scenes in egocentric photo-streams
• Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments
• Structural Consistency and Controllability for Diverse Colorization
• Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss
• Woodbury Transformations for Deep Generative Flows
• A Novel Framework for Selection of GANs for an Application
• Shifting Transformation Learning for Out-of-Distribution Detection
• On Out-of-distribution Detection with Energy-based Models
• Perceptual Image Super-Resolution with Progressive Adversarial Network
• Being a Bit Frequentist Improves Bayesian Neural Networks
• Curriculum Learning for Deep Generative Models with Clustering
• Masked Contrastive Learning for Anomaly Detection
• Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior
• Ensembling with Deep Generative Views
• On Positive-Unlabeled Classification in GAN
• Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
• Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection
• Generative Adversarial Data Programming
• A Method for Identifying Origin of Digital Images Using a Convolution Neural Network
• Blur, Noise, and Compression Robust Generative Adversarial Networks
• Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers
• Tessellated Wasserstein Auto-Encoders
• A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples
• Toward Scalable and Unified Example-based Explanation and Outlier Detection
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• Deep Residual Flow for Out of Distribution Detection
• LatentKeypointGAN: Controlling Images via Latent Keypoints
• Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
• MOOD: Multi-level Out-of-distribution Detection
• Robust Training Using Natural Transformation
• Low-Rank Subspaces in GANs
• Self-supervised GAN Detector
• Human-In-The-Loop Document Layout Analysis
• A Memristor based Unsupervised Neuromorphic System Towards Fast and Energy-Efficient GAN
• Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features
• Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery
• CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning
• Generating Memorable Images Based on Human Visual Memory Schemas
• Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling
• Unsupervised Adversarial Image Inpainting
• AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
• Relevant-features based Auxiliary Cells for Energy Efficient Detection of Natural Errors
• Kernel Mean Matching for Content Addressability of GANs
• Improving Generative Adversarial Networks with Local Coordinate Coding
• Deep Automodulators
• On the Frequency Bias of Generative Models
• StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN
• PixelPyramids: Exact Inference Models from Lossless Image Pyramids
• Open-set Adversarial Defense
• RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View
• Toward a Realistic Benchmark for Out-of-Distribution Detection
• Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
• EdiBERT, a generative model for image editing
• Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data
• Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
• Knowledge-driven Active Learning
• Representation Learning: A Statistical Perspective
• Linear Discriminant Generative Adversarial Networks
• When Relation Networks meet GANs: Relation GANs with Triplet Loss
• Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
• Exploring Adversarial Fake Images on Face Manifold
• Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
• FRAME Revisited: An Interpretation View Based on Particle Evolution
• RealisticHands: A Hybrid Model for 3D Hand Reconstruction
• Greedy Bayesian Posterior Approximation with Deep Ensembles
• Inducing Hierarchical Compositional Model by Sparsifying Generator Network
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks
• [RE] CNN-generated images are surprisingly easy to spot...for now
• Noise Robust Generative Adversarial Networks
• Unsupervised Image Transformation Learning via Generative Adversarial Networks
• Linear Semantics in Generative Adversarial Networks
• An Image-based Approach of Task-driven Driving Scene Categorization
• BSD-GAN: Branched Generative Adversarial Network for Scale-Disentangled Representation Learning and Image Synthesis