mlsanityData to 14 Oct 2026

MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier

arXiv 2209.11549 ↗First posted 23 Sep 2022cs.CV cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers. Our proposed method, entitled MAGIC, leverages structured gradients from a pre-trained quasi-robust classifier to better preserve the input semantics while preserving its classification accuracy, thereby guaranteeing credibility in the synthesis. Unlike current methods that use complex primitives to supervise the process or use attention maps as a weak supervisory signal, MAGIC aggregates gradients over the input, driven by a guide binary mask that enforces a strong, spatial prior. MAGIC implements a series of manipulations with a single framework achieving shape and location control, intense non-rigid shape deformations, and copy/move operations in the presence of repeating objects and gives users firm control over the synthesis by requiring to simply specify binary guide masks. Our study and findings are supported by various qualitative comparisons with the state-of-the-art on the same images sampled from ImageNet and quantitative analysis using machine perception along with a user survey of 100+ participants that endorse our synthesis quality. Project page at https://mozhdehrouhsedaghat.github.io/magic.html. Code is available at https://github.com/mozhdehrouhsedaghat/magic

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 23 Sep 2022.

Builds on

33 of 46 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2017Improved Training of Wasserstein GANscited by 2,235
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  11. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  12. 2018Robustness May Be at Odds with Accuracycited by 880
21 more
  1. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  2. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  3. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  4. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  5. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 316
  6. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 288
  7. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  8. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  9. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  10. 2019Interpreting Adversarially Trained Convolutional Neural Networkscited by 75
  11. 2019Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generationcited by 75
  12. 2019Mask-Guided Portrait Editing with Conditional GANscited by 61
  13. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  14. 2021Diverse Semantic Image Synthesis via Probability Distribution Modelingcited by 49
  15. 2019Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?cited by 43
  16. 2021IMAGINE: Image Synthesis by Image-Guided Model Inversioncited by 25
  17. 2019Bridging Adversarial Robustness and Gradient Interpretabilitycited by 22
  18. 2020On the Benefits of Models with Perceptually-Aligned Gradientscited by 13
  19. 2020Image Shape Manipulation from a Single Augmented Training Samplecited by 13
  20. 2020Adversarial Training Reduces Information and Improves Transferabilitycited by 10
  21. 2021Inverting Adversarially Robust Networks for Image Synthesiscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2024Shedding More Light on Robust Classifiers under the lens of Energy-based Modelscited by 9
  2. 2023Exploring the Connection between Robust and Generative Modelscited by 2
  3. 2023pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptationcited by 2
  4. 2025Understanding Adversarial Training with Energy-based Modelscited by 2
  5. 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Modelscited by 1
  6. 2024Environment Maps Editing using Inverse Rendering and Adversarial Implicit Functionscited by 0