ImageNet
Canonical122papers using it
9,123HF downloads
2HF likes
2016first seen
~1.28M labeled images across 1,000 categories (ILSVRC) — the standard large-scale image-classification benchmark.
Papers using ImageNet (117)
- Generative Modeling via DriftingThe GAN is dead; long live the GAN! A Modern GAN BaselineOne-step Latent-free Image Generation with Pixel Mean FlowsRAD: Region-Aware Diffusion Models for Image InpaintingOne-Step Residual Shifting Diffusion for Image Super-Resolution via DistillationPQD: Post-training Quantization for Efficient Diffusion ModelsData Pruning in Generative Diffusion ModelsEnd-to-End Autoregressive Image Generation with 1D Semantic TokenizerLearning Discrete Autoregressive Priors with Wasserstein Gradient FlowFrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel DiffusionDual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light networkNormalizing Flows with Iterative DenoisingVariational Flow Maps: Make Some Noise for One-Step Conditional GenerationEnd-to-End Training for Unified Tokenization and Latent DenoisingLatent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image GenerationExpanding the Role of Diffusion Models for Robust Classifier TrainingU-Turn DiffusionIGAN: A New Inception-based Model for Stable and High-Fidelity Image Synthesis Using Generative Adversarial NetworksMultilevel and Sequential Monte Carlo for Training-Free Diffusion GuidanceDistribution Matching Variational AutoEncoderDiffusion As Self-Distillation: End-to-End Latent Diffusion In One ModelDiP: Taming Diffusion Models in Pixel SpaceDeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image GenerationThere is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-trainingDiffusion Transformers with Representation AutoencodersIS-Diff: Improving Diffusion-Based Inpainting with Better Initial SeedLowDiff: Efficient Diffusion Sampling with Low-Resolution ConditionDiscrete Variational Autoencoding via Policy SearchHiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion ModelsAccelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based PerspectiveLearning Diffusion Models with Flexible Representation GuidanceCompositional Discrete Latent Code for High Fidelity, Productive Diffusion ModelsLatent Stochastic InterpolantsAligning Latent Spaces with Flow PriorsDiffuse and Disperse: Image Generation with Representation RegularizationAmbient Diffusion Omni: Training Good Models with Bad DataDiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion ModelingPixelFlow: Pixel-Space Generative Models with FlowEntropic Time Schedulers for Generative Diffusion ModelsReconciling Stochastic and Deterministic Strategies for Zero-shot Image
Restoration using Diffusion Model in DualControlling Latent Diffusion Using Latent CLIPDiffMoE: Dynamic Token Selection for Scalable Diffusion TransformersMasked Autoencoders Are Effective Tokenizers for Diffusion ModelsDiffusion Models for Inverse Problems in the Exponential FamilyDiffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial PurifierGuiding a diffusion model using sliding windowsDenoising with a Joint-Embedding Predictive ArchitectureImproving Vector-Quantized Image Modeling with Latent
Consistency-Matching DiffusionUnlocking Dataset Distillation with Diffusion ModelsSpatial-and-Frequency-aware Restoration method for Images based on Diffusion ModelsLarge Scale GAN Training for High Fidelity Natural Image SynthesisConditional Image Synthesis With Auxiliary Classifier GANsCascaded Diffusion Models for High Fidelity Image GenerationLarge Scale Adversarial Representation LearningProgressive Distillation for Fast Sampling of Diffusion ModelsBoundary-Seeking Generative Adversarial NetworksDiffEdit: Diffusion-based semantic image editing with mask guidanceHigh-Fidelity Image Generation With Fewer LabelsAuto-Embedding Generative Adversarial Networks for High Resolution Image
SynthesisSynthetic Data from Diffusion Models Improves ImageNet ClassificationContraGAN: Contrastive Learning for Conditional Image GenerationLOGAN: Latent Optimisation for Generative Adversarial NetworksImage Super-Resolution via Iterative RefinementEmerging Convolutions for Generative Normalizing FlowsDiffusionCLIP: Text-Guided Diffusion Models for Robust Image
ManipulationAccelerating Diffusion Models via Early Stop of the Diffusion ProcessOn the Importance of Noise Scheduling for Diffusion ModelsSimple diffusion: End-to-end diffusion for high resolution imagesHierarchical Autoregressive Image Models with Auxiliary DecodersTransferring GANs: generating images from limited dataDiscriminator optimal transportEfficient Conditional Diffusion Model with Probability Flow Sampling for
Image Super-resolutionImproving the Speed and Quality of GAN by Adversarial TrainingTraining Generative Adversarial Networks by Solving Ordinary
Differential EquationsUnderstanding Diffusion Objectives as the ELBO with Simple Data
AugmentationRegularizing Generative Adversarial Networks under Limited DataDiVAE: Photorealistic Images Synthesis with Denoising Diffusion DecoderDenoising Diffusion Models for Plug-and-Play Image RestorationSelf-Supervised GANs via Auxiliary Rotation LossData-Efficient GAN Training Beyond (Just) Augmentations: A Lottery
Ticket PerspectiveDenoising Diffusion Autoencoders are Unified Self-supervised LearnersDeepCache: Accelerating Diffusion Models for FreePhotorealistic Video Generation with Diffusion ModelsTowards Efficient Diffusion-Based Image Editing with Instant Attention
MaskscGANs with Conditional Convolution LayerGuiding a Diffusion Model with a Bad Version of Itself3D-aware Image Generation using 2D Diffusion ModelsG3DR: Generative 3D Reconstruction in ImageNetDiffSmooth: Certifiably Robust Learning via Diffusion Models and Local
SmoothingCADS: Unleashing the Diversity of Diffusion Models through
Condition-Annealed SamplingFixed Point Diffusion ModelsCondition-Aware Neural Network for Controlled Image GenerationHow good is my GAN?Diverse Image Generation via Self-Conditioned GANsTinyGAN: Distilling BigGAN for Conditional Image GenerationOmni-GAN: On the Secrets of cGANs and Beyondf-DM: A Multi-stage Diffusion Model via Progressive Signal
TransformationTF-ICON: Diffusion-Based Training-Free Cross-Domain Image CompositionExploring Transformer Backbones for Image Diffusion ModelsMimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean
Diffusion ModelFine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious
Feature GenerationT-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with
Trajectory StitchingSD-DiT: Unleashing the Power of Self-supervised Discrimination in
Diffusion TransformerPaGoDA: Progressive Growing of a One-Step Generator from a
Low-Resolution Diffusion TeacherMultistep Distillation of Diffusion Models via Moment MatchingFast Flow Reconstruction via Robust Invertible nxn ConvolutionGenerative Adversarial Learning via Kernel Density DiscriminationPalette: Image-to-Image Diffusion ModelsImproved Masked Image Generation with Token-CriticZero-Shot Learning of a Conditional Generative Adversarial Network for
Data-Free Network QuantizationFast Inference in Denoising Diffusion Models via MMD FinetuningNested Diffusion Processes for Anytime Image GenerationMCGAN: Enhancing GAN Training with Regression-Based Generator LossFast Samplers for Inverse Problems in Iterative Refinement ModelsShedding Light on Large Generative Networks: Estimating Epistemic
Uncertainty in Diffusion ModelsDiffusion Models For Multi-Modal Generative ModelingPruning then Reweighting: Towards Data-Efficient Training of Diffusion
Models