mlsanityData to 7 Oct 2026

Diverse Image Generation via Self-Conditioned GANs

arXiv 2006.10728 ↗First posted 18 Jun 2020cs.CV cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

We introduce a simple but effective unsupervised method for generating realistic and diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels automatically derived from clustering in the discriminator's feature space. Our clustering step automatically discovers diverse modes, and explicitly requires the generator to cover them. Experiments on standard mode collapse benchmarks show that our method outperforms several competing methods when addressing mode collapse. Our method also performs well on large-scale datasets such as ImageNet and Places365, improving both image diversity and standard quality metrics, compared to previous methods.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 16; 2023: 7; 2024: 7; 2025: 5; 2026: 3.

54 papers.

Sort:

By area:

  1. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 610
  2. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  3. 2024The Platonic Representation Hypothesiscited by 362
  4. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 299
  5. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 222
  6. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  7. 2021Instance-Conditioned GANcited by 119
  8. 2023Return of Unconditional Generation: A Self-supervised Representation Generation Methodcited by 95
  9. 2021Improved Transformer for High-Resolution GANscited by 59
  10. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  11. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  12. 2021Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Modelscited by 44
38 more
  1. 2022Self-Distilled StyleGAN: Towards Generation from Internet Photoscited by 37
  2. 2023Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labelscited by 37
  3. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  4. 2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
  5. 2023KD-DLGAN: Data Limited Image Generation via Knowledge Distillationcited by 16
  6. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  7. 2024Diffusion Posterior Proximal Sampling for Image Restorationcited by 14
  8. 2021MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminatorscited by 11
  9. 2022Secure Federated Clusteringcited by 10
  10. 2021Partition-Guided GANscited by 9
  11. 2021Contrastive Fine-grained Class Clustering via Generative Adversarial Networkscited by 9
  12. 2022Improved Input Reprogramming for GAN Conditioningcited by 7
  13. 2022Unsupervised Learning of Structured Representations via Closed-Loop Transcriptioncited by 7
  14. 2022Do DALL-E and Flamingo Understand Each Other?cited by 7
  15. 2023Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learningcited by 7
  16. 2021Ensembles of GANs for synthetic training data generationcited by 6
  17. 2022Self-Conditioned Generative Adversarial Networks for Image Editingcited by 6
  18. 2022LANIT: Language-Driven Image-to-Image Translation for Unlabeled Datacited by 5
  19. 2024Rethinking cluster-conditioned diffusion models for label-free image synthesiscited by 5
  20. 2025Measuring Diversity in Synthetic Datasetscited by 5
  21. 2022Multi-level Latent Space Structuring for Generative Controlcited by 4
  22. 2024Ambiguous Annotations: When is a Pedestrian not a Pedestrian?cited by 4
  23. 2021Cluster-guided Image Synthesis with Unconditional Modelscited by 3
  24. 2022Diversity in deep generative models and generative AIcited by 2
  25. 2023Structural Adversarial Objectives for Self-Supervised Representation Learningcited by 2
  26. 2025Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generationcited by 2
  27. 2021IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapsecited by 1
  28. 2021Stein Latent Optimization for Generative Adversarial Networkscited by 1
  29. 2021Unsupervised Image Generation with Infinite Generative Adversarial Networkscited by 1
  30. 2022S2-Flow: Joint Semantic and Style Editing of Facial Imagescited by 1
  31. 2024MS3D: A RG Flow-Based Regularization for GAN Training with Limited Datacited by 1
  32. 2021Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matchingcited by 0
  33. 2021Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generatorscited by 0
  34. 2022Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networkscited by 0
  35. 2023Likely, Light, and Accurate Context-Free Clusters-based Trajectory Predictioncited by 0
  36. 2024Beyond Traditional Single Object Tracking: A Surveycited by 0
  37. 2025Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesiscited by 0
  38. 2025Style Quantization for Data-Efficient GAN Trainingcited by 0

50 most cited of 54 All 54 (JSON)