mlsanityData to 7 Oct 2026

GANalyze: Toward Visual Definitions of Cognitive Image Properties

arXiv 1906.10112 ↗First posted 24 Jun 2019cs.CVcited by 193

Not on the map. Why?

Abstract (arXiv)

We introduce a framework that uses Generative Adversarial Networks (GANs) to study cognitive properties like memorability, aesthetics, and emotional valence. These attributes are of interest because we do not have a concrete visual definition of what they entail. What does it look like for a dog to be more or less memorable? GANs allow us to generate a manifold of natural-looking images with fine-grained differences in their visual attributes. By navigating this manifold in directions that increase memorability, we can visualize what it looks like for a particular generated image to become more or less memorable. The resulting ``visual definitions" surface image properties (like ``object size") that may underlie memorability. Through behavioral experiments, we verify that our method indeed discovers image manipulations that causally affect human memory performance. We further demonstrate that the same framework can be used to analyze image aesthetics and emotional valence. Visit the GANalyze website at http://ganalyze.csail.mit.edu/.

Key facts. Cited by 193 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 58; 2022: 68; 2023: 35; 2024: 13; 2025: 8; 2026: 11.

193 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  2. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  4. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  5. 2021GAN Inversion: A Surveycited by 366
  6. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  7. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  8. 2023Interpreting CLIP's Image Representation via Text-Based Decompositioncited by 189
  9. 2022Latent Image Animator: Learning to Animate Images via Latent Space Navigationcited by 172
  10. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  11. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  12. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
38 more
  1. 2021Paint by Wordcited by 107
  2. 2021Generative Models as a Data Source for Multiview Representation Learningcited by 104
  3. 2021Only a Matter of Style: Age Transformation Using a Style-Based Regression Modelcited by 92
  4. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  5. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  6. 2021HairCLIP: Design Your Hair by Text and Reference Imagecited by 79
  7. 2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
  8. 2023StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editingcited by 68
  9. 2021A Latent Transformer for Disentangled Face Editing in Images and Videoscited by 67
  10. 2021Controllable and Compositional Generation with Latent-Space Energy-Based Modelscited by 64
  11. 2021Editing a classifier by rewriting its prediction rulescited by 64
  12. 2022Disentangling visual and written concepts in CLIPcited by 57
  13. 2021Using latent space regression to analyze and leverage compositionality in GANscited by 55
  14. 2021CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fieldscited by 55
  15. 2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
  16. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  17. 2021LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directionscited by 52
  18. 2021Low-Rank Subspaces in GANscited by 52
  19. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  20. 2021WarpedGANSpace: Finding non-linear RBF paths in GAN latent spacecited by 48
  21. 2023Rosetta Neurons: Mining the Common Units in a Model Zoocited by 46
  22. 2023NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Modelscited by 46
  23. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  24. 2022Self-Distilled StyleGAN: Towards Generation from Internet Photoscited by 37
  25. 2022TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editingcited by 36
  26. 2022Text and Image Guided 3D Avatar Generation and Manipulationcited by 35
  27. 2022BlobGAN: Spatially Disentangled Scene Representationscited by 35
  28. 2021EigenGAN: Layer-Wise Eigen-Learning for GANscited by 34
  29. 2022Guided Co-Modulated GAN for 360deg Field of View Extrapolationcited by 32
  30. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 29
  31. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  32. 2021StyleFusion: A Generative Model for Disentangling Spatial Segmentscited by 28
  33. 2022FlexIT: Towards Flexible Semantic Image Translationcited by 28
  34. 2021CoMoGAN: continuous model-guided image-to-image translationcited by 27
  35. 2021Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANscited by 26
  36. 2021From Continuity to Editability: Inverting GANs with Consecutive Imagescited by 25
  37. 2021Improving GAN Equilibrium by Raising Spatial Awarenesscited by 22
  38. 2022Region-Based Semantic Factorization in GANscited by 22

50 most cited of 193 All 193 (JSON)