mlsanityData to 7 Oct 2026

LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions

arXiv 2104.00820 ↗First posted 2 Apr 2021cs.LG cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of semantic editing operations, such as zoom or rotation. The discovery of such directions is often done in a supervised or semi-supervised manner and requires manual annotations which limits their use in practice. In comparison, unsupervised discovery allows finding subtle directions that are difficult to detect a priori. In this work, we propose a contrastive learning-based approach to discover semantic directions in the latent space of pre-trained GANs in a self-supervised manner. Our approach finds semantically meaningful dimensions comparable with state-of-the-art methods.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 2 Apr 2021.

Builds on

29 of 40 references.

References · 29

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  10. 2019Contrastive Multiview Codingcited by 1,297
  11. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  12. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
17 more
  1. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  2. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  3. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  4. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  5. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  6. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  7. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  8. 2019On the "steerability" of generative adversarial networkscited by 247
  9. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  10. 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 208
  11. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  12. 2019Spatial Attentive Single-Image Deraining with a High Quality Real Rain Datasetcited by 192
  13. 2020Controlling generative models with continuous factors of variationscited by 93
  14. 2019Single Image Deraining: A Comprehensive Benchmark Analysiscited by 84
  15. 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
  16. 2020Navigating the GAN Parameter Space for Semantic Image Editingcited by 49
  17. 2020GAN "Steerability" without optimizationcited by 48

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 22; 2023: 14; 2024: 6; 2025: 3; 2026: 3.

52 papers.

Sort:

By area:

  1. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  2. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  3. 2023Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometrycited by 121
  4. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  5. 2023NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Modelscited by 46
  6. 20223D GAN Inversion with Pose Optimizationcited by 44
  7. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  8. 2022Style Transformer for Image Inversion and Editingcited by 37
  9. 2022Text and Image Guided 3D Avatar Generation and Manipulationcited by 35
  10. 2022Temporally Consistent Semantic Video Editingcited by 28
  11. 2022User-Controllable Latent Transformer for StyleGAN Image Layout Editingcited by 28
  12. 2023Unsupervised Discovery of Semantic Latent Directions in Diffusion Modelscited by 28
38 more
  1. 2022Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Explorationcited by 21
  2. 2022FairStyle: Debiasing StyleGAN2 with Style Channel Manipulationscited by 20
  3. 2022Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpointcited by 18
  4. 2023Hierarchical Diffusion Autoencoders and Disentangled Image Manipulationcited by 18
  5. 2022GAN-based Facial Attribute Manipulationcited by 16
  6. 2022A Survey on Deep Generative 3D-aware Image Synthesiscited by 16
  7. 2022UnGANable: Defending Against GAN-based Face Manipulationcited by 15
  8. 2023LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesiscited by 15
  9. 2021Deep Bregman Divergence for Contrastive Learning of Visual Representationscited by 13
  10. 2023RIGID: Recurrent GAN Inversion and Editing of Real Face Videoscited by 13
  11. 2022IA-FaceS: A Bidirectional Method for Semantic Face Editingcited by 8
  12. 2022Hierarchical Semantic Regularization of Latent Spaces in StyleGANscited by 8
  13. 2022End-to-End Visual Editing with a Generatively Pre-Trained Artistcited by 7
  14. 2022FurryGAN: High Quality Foreground-aware Image Synthesiscited by 6
  15. 2023Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Modelscited by 6
  16. 2024Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Modelscited by 6
  17. 2022LatentSwap3D: Semantic Edits on 3D Image GANscited by 5
  18. 2022Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANscited by 4
  19. 2022Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spacescited by 4
  20. 2024The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIPcited by 4
  21. 2023Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Modelscited by 2
  22. 2023Meta-Auxiliary Network for 3D GAN Inversioncited by 2
  23. 2023Identity-preserving Editing of Multiple Facial Attributes by Learning Global Edit Directions and Local Adjustmentscited by 2
  24. 2025Discovering Intersectional Bias via Directional Alignment in Face Recognition Embeddingscited by 2
  25. 2022Discovering Class-Specific GAN Controls for Semantic Image Synthesiscited by 1
  26. 2023StyleHumanCLIP: Text-guided Garment Manipulation for StyleGAN-Humancited by 1
  27. 2023Exploring Attribute Variations in Style-based GANs using Diffusion Modelscited by 1
  28. 2024AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglementcited by 1
  29. 2022Discovering Multiple and Diverse Directions for Cognitive Image Propertiescited by 0
  30. 2022ContraFeat: Contrasting Deep Features for Semantic Discoverycited by 0
  31. 2023Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creationcited by 0
  32. 2023Feature Noise Boosts DNN Generalization under Label Noisecited by 0
  33. 2024SwinStyleformer is a favorable choice for image inversioncited by 0
  34. 2024Disentangling Regional Primitives for Image Generationcited by 0
  35. 2024Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantizationcited by 0
  36. 2025DiffEx: Explaining a Classifier with Diffusion Models to Identify Microscopic Cellular Variationscited by 0
  37. 2025Efficient Few-shot Identity Preserving Attribute Editing for 3D-aware Deep Generative Modelscited by 0
  38. 2026PixelSmile: Toward Fine-Grained Facial Expression Editingcited by 0

50 most cited of 52 All 52 (JSON)