mlsanityData to 7 Oct 2026

Image-to-image Translation via Hierarchical Style Disentanglement

arXiv 2103.01456 ↗First posted 2 Mar 2021cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

Recently, image-to-image translation has made significant progress in achieving both multi-label (ie, translation conditioned on different labels) and multi-style (ie, generation with diverse styles) tasks. However, due to the unexplored independence and exclusiveness in the labels, existing endeavors are defeated by involving uncontrolled manipulations to the translation results. In this paper, we propose Hierarchical Style Disentanglement (HiSD) to address this issue. Specifically, we organize the labels into a hierarchical tree structure, in which independent tags, exclusive attributes, and disentangled styles are allocated from top to bottom. Correspondingly, a new translation process is designed to adapt the above structure, in which the styles are identified for controllable translations. Both qualitative and quantitative results on the CelebA-HQ dataset verify the ability of the proposed HiSD. We hope our method will serve as a solid baseline and provide fresh insights with the hierarchically organized annotations for future research in image-to-image translation. The code has been released at https://github.com/imlixinyang/HiSD.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 50 of its 57 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

50 of 57 references.

References · 50

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
38 more
  1. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  2. 2016Colorful Image Colorizationcited by 1,113
  3. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  4. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  5. 2016Least Squares Generative Adversarial Networkscited by 1,000
  6. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  7. 2016Generative Adversarial Text to Image Synthesiscited by 735
  8. 2018Which Training Methods for GANs do actually Converge?cited by 672
  9. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  10. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  11. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  12. 2017Toward Multimodal Image-to-Image Translationcited by 295
  13. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  14. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  15. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  16. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  17. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  18. 2017Real-Time Adaptive Image Compressioncited by 127
  19. 2016Unsupervised Cross-Domain Image Generationcited by 125
  20. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 119
  21. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
  22. 2018Unsupervised Attention-guided Image to Image Translationcited by 58
  23. 2019RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributescited by 56
  24. 2018ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributescited by 50
  25. 2019SPA-GAN: Spatial Attention GAN for Image-to-Image Translationcited by 43
  26. 2019Multi-mapping Image-to-Image Translation via Learning Disentanglementcited by 35
  27. 2018SMIT: Stochastic Multi-Label Image-to-Image Translationcited by 21
  28. 2019Domain Intersection and Domain Differencecited by 17
  29. 2017DNA-GAN: Learning Disentangled Representations from Multi-Attribute Imagescited by 16
  30. 2018Modular Generative Adversarial Networkscited by 16
  31. 2020Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfercited by 15
  32. 2017GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Datacited by 11
  33. 2019SDIT: Scalable and Diverse Cross-domain Image Translationcited by 11
  34. 2019Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learningcited by 8
  35. 2019Mask Based Unsupervised Content Transfercited by 8
  36. 2019MulGAN: Facial Attribute Editing by Exemplarcited by 8
  37. 2019Information Competing Process for Learning Diversified Representationscited by 6
  38. 2017SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolutioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 17; 2023: 12; 2024: 12; 2025: 9; 2026: 6.

63 papers.

Sort:

By area:

  1. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  2. 2022Disentangled Representation Learningcited by 111
  3. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  4. 2021CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakescited by 54
  5. 2022Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translationcited by 39
  6. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  7. 2022Controllable 3D Face Synthesis with Conditional Generative Occupancy Fieldscited by 37
  8. 2021Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Modelcited by 34
  9. 2023Diverse Inpainting and Editing with GAN Inversioncited by 20
  10. 2023Detecting Generated Images by Real Images Onlycited by 20
  11. 2022Interactive Image Synthesis with Panoptic Layout Generationcited by 17
  12. 2022VecGAN: Image-to-Image Translation with Interpretable Latent Directionscited by 17
38 more
  1. 2022GAN-based Facial Attribute Manipulationcited by 16
  2. 2024Language-guided Hierarchical Fine-grained Image Forgery Detection and Localizationcited by 16
  3. 2023Image-to-Image Translation with Disentangled Latent Vectors for Face Editingcited by 13
  4. 2023AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detectioncited by 12
  5. 2022Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Datacited by 11
  6. 2022Region-aware Knowledge Distillation for Efficient Image-to-Image Translationcited by 10
  7. 2023Text-guided Eyeglasses Manipulation with Spatial Constraintscited by 10
  8. 2021Physics-informed Guided Disentanglement in Generative Networkscited by 9
  9. 2023Information-containing Adversarial Perturbation for Combating Facial Manipulation Systemscited by 9
  10. 2023Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generationcited by 9
  11. 2024Reference-Based 3D-Aware Image Editing with Triplanescited by 9
  12. 2024Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Modelscited by 9
  13. 2024FaceShield: Defending Facial Image against Deepfake Threatscited by 8
  14. 2021DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editingcited by 7
  15. 2022Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translationcited by 6
  16. 2023A Survey of Methods, Challenges and Perspectives in Causalitycited by 6
  17. 2023Warping the Residuals for Image Editing with StyleGANcited by 6
  18. 2024FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editingcited by 6
  19. 2022PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generationcited by 5
  20. 2022Do Inpainting Yourself: Generative Facial Inpainting Guided by Exemplarscited by 4
  21. 2024ID-Guard: A Universal Framework for Combating Facial Manipulation via Breaking Identificationcited by 4
  22. 2022Design What You Desire: Icon Generation from Orthogonal Application and Theme Labelscited by 3
  23. 2023Feature Extraction Matters More: Universal Deepfake Disruption through Attacking Ensemble Feature Extractorscited by 3
  24. 2024A Large-scale Universal Evaluation Benchmark For Face Forgery Detectioncited by 3
  25. 2025Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensicscited by 3
  26. 2022CCR: Facial Image Editing with Continuity, Consistency and Reversibilitycited by 2
  27. 2022Masked Reconstruction Contrastive Learning with Information Bottleneck Principlecited by 2
  28. 2024CoroNetGAN: Controlled Pruning of GANs via Hypernetworkscited by 2
  29. 2024OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variationscited by 2
  30. 2025COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Stylescited by 2
  31. 2025Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfercited by 2
  32. 2025Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfakecited by 2
  33. 2022ChildPredictor: A Child Face Prediction Framework with Disentangled Learningcited by 1
  34. 2024An Analysis for Image-to-Image Translation and Style Transfercited by 1
  35. 2026Enhancing Visual In-Context Learning by Multi-Faceted Fusioncited by 1
  36. 2026Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editingcited by 1
  37. 2026Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulationscited by 1
  38. 2021Delving into Rectifiers in Style-Based Image Translationcited by 0

50 most cited of 63 All 63 (JSON)