mlsanityData to 7 Oct 2026

IMAGINE: Image Synthesis by Image-Guided Model Inversion

arXiv 2104.05895 ↗First posted 13 Apr 2021cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

We introduce an inversion based method, denoted as IMAge-Guided model INvErsion (IMAGINE), to generate high-quality and diverse images from only a single training sample. We leverage the knowledge of image semantics from a pre-trained classifier to achieve plausible generations via matching multi-level feature representations in the classifier, associated with adversarial training with an external discriminator. IMAGINE enables the synthesis procedure to simultaneously 1) enforce semantic specificity constraints during the synthesis, 2) produce realistic images without generator training, and 3) give users intuitive control over the generation process. With extensive experimental results, we demonstrate qualitatively and quantitatively that IMAGINE performs favorably against state-of-the-art GAN-based and inversion-based methods, across three different image domains (i.e., objects, scenes, and textures).

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

35 of 48 references.

References · 35

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
23 more
  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2014Conditional Generative Adversarial Netscited by 2,152
  3. 2013Describing Textures in the Wildcited by 2,110
  4. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  5. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  6. 2017Wasserstein GANcited by 635
  7. 2017One pixel attack for fooling deep neural networkscited by 579
  8. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  9. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  10. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  11. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  12. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  13. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  14. 2019Counterfactual Visual Explanationscited by 312
  15. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  16. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  17. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  18. 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
  19. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  20. 2019Seeing What a GAN Cannot Generatecited by 148
  21. 2020SCOUT: Self-aware Discriminant Counterfactual Explanationscited by 52
  22. 2021Rethinking and Improving the Robustness of Image Style Transfercited by 48
  23. 2020Semantic Pyramid for Image Generationcited by 34

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 8; 2023: 7; 2024: 5; 2025: 2.

25 papers.

Sort:

By area:

  1. 2021Unsolved Problems in ML Safetycited by 291
  2. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensingcited by 150
  3. 2022Diffusion Models for Counterfactual Explanationscited by 79
  4. 2022Expanding Small-Scale Datasets with Guided Imaginationcited by 61
  5. 2023M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalitiescited by 56
  6. 2023Adversarial Counterfactual Visual Explanationscited by 47
  7. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  8. 2023Latent Diffusion Counterfactual Explanationscited by 17
  9. 2022PetsGAN: Rethinking Priors for Single Image Generationcited by 14
  10. 2023Feature Matching Data Synthesis for Non-IID Federated Learningcited by 13
  11. 2021ExSinGAN: Learning an Explainable Generative Model from a Single Imagecited by 12
  12. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
13 more
  1. 2023NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistencycited by 7
  2. 2022MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifiercited by 6
  3. 2022SIAN: Style-Guided Instance-Adaptive Normalization for Multi-Organ Histopathology Image Synthesiscited by 5
  4. 2024Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographscited by 3
  5. 2023pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptationcited by 2
  6. 2022One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPUcited by 1
  7. 2025Counterfactual Visual Explanation via Causally-Guided Adversarial Steeringcited by 1
  8. 2025CCSD: Cross-Modal Compositional Self-Distillation for Robust Brain Tumor Segmentation with Missing Modalitiescited by 1
  9. 2021Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layerscited by 0
  10. 2022Computer Vision-based Characterization of Large-scale Jet Flames using a Synthetic Infrared Image Generation Approachcited by 0
  11. 2024Transferring Ultrahigh-Field Representations for Intensity-Guided Brain Segmentation of Low-Field Magnetic Resonance Imagingcited by 0
  12. 2024DataFreeShield: Defending Adversarial Attacks without Training Datacited by 0
  13. 2024Environment Maps Editing using Inverse Rendering and Adversarial Implicit Functionscited by 0