mlsanityData to 7 Oct 2026

Generative Hierarchical Features from Synthesizing Images

arXiv 2007.10379 ↗First posted 20 Jul 2020cs.CVcited by 83

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data. However, how the features learned from solving the task of image generation are applicable to other vision tasks remains seldom explored. In this work, we show that learning to synthesize images can bring remarkable hierarchical visual features that are generalizable across a wide range of applications. Specifically, we consider the pre-trained StyleGAN generator as a learned loss function and utilize its layer-wise representation to train a novel hierarchical encoder. The visual feature produced by our encoder, termed as Generative Hierarchical Feature (GH-Feat), has strong transferability to both generative and discriminative tasks, including image editing, image harmonization, image classification, face verification, landmark detection, and layout prediction. Extensive qualitative and quantitative experimental results demonstrate the appealing performance of GH-Feat.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 28; 2023: 25; 2024: 5; 2025: 4; 2026: 1.

83 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  2. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  3. 2021GAN Inversion: A Surveycited by 366
  4. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  5. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  6. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 222
  7. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  8. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  9. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  10. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  11. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  12. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
38 more
  1. 2022DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesiscited by 61
  2. 2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
  3. 2021Labels4Free: Unsupervised Segmentation using StyleGANcited by 53
  4. 2021Low-Rank Subspaces in GANscited by 52
  5. 2022Region-Aware Face Swappingcited by 45
  6. 2022SceneComposer: Any-Level Semantic Image Synthesiscited by 43
  7. 2021One-Shot Generative Domain Adaptationcited by 41
  8. 2023DreamTeacher: Pretraining Image Backbones with Deep Generative Modelscited by 37
  9. 2023Exploiting Diffusion Prior for Generalizable Dense Predictioncited by 37
  10. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  11. 20243DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splattingcited by 25
  12. 2022High-fidelity GAN Inversion with Padding Spacecited by 23
  13. 2022Region-Based Semantic Factorization in GANscited by 22
  14. 2022Improving GANs with A Dynamic Discriminatorcited by 20
  15. 2022GLEAN: Generative Latent Bank for Image Super-Resolution and Beyondcited by 19
  16. 2023StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generationcited by 19
  17. 2023Hierarchical Diffusion Autoencoders and Disentangled Image Manipulationcited by 18
  18. 2023LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysiscited by 18
  19. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  20. 2022FEAT: Face Editing with Attentioncited by 16
  21. 2021Retrieve in Style: Unsupervised Facial Feature Transfer and Retrievalcited by 15
  22. 2022High-Fidelity Image Inpainting with GAN Inversioncited by 15
  23. 2023LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesiscited by 15
  24. 2021StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGANcited by 14
  25. 2022Editing Out-of-domain GAN Inversion via Differential Activationscited by 14
  26. 2023Learning 3D-aware Image Synthesis with Unknown Pose Distributioncited by 14
  27. 2021Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulationcited by 13
  28. 2023Exploring Sparse MoE in GANs for Text-conditioned Image Synthesiscited by 13
  29. 2022ContraCLIP: Interpretable GAN generation driven by pairs of contrasting sentencescited by 12
  30. 2023FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Featurescited by 12
  31. 2023Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Visioncited by 11
  32. 2024Real-time 3D-aware Portrait Editing from a Single Imagecited by 10
  33. 2024How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?cited by 10
  34. 2024Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencodercited by 10
  35. 2023Make It So: Steering StyleGAN for Any Image Inversion and Editingcited by 9
  36. 2021Unsupervised Novel View Synthesis from a Single Imagecited by 8
  37. 2023Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wildcited by 8
  38. 2021InvGAN: Invertible GANscited by 7

50 most cited of 83 All 83 (JSON)