mlsanityData to 7 Oct 2026

Good Semi-supervised Learning that Requires a Bad GAN

arXiv 1705.09783 ↗First posted 27 May 2017cs.LG cs.AIcited by 85

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised classification performance and a good generator cannot be obtained at the same time. Theoretically, we show that given the discriminator objective, good semisupervised learning indeed requires a bad generator, and propose the definition of a preferred generator. Empirically, we derive a novel formulation based on our analysis that substantially improves over feature matching GANs, obtaining state-of-the-art results on multiple benchmark datasets.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 22; 2023: 15; 2024: 11; 2025: 7; 2026: 2.

85 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  3. 2021A Survey on Deep Semi-supervised Learningcited by 250
  4. 2023A Cookbook of Self-Supervised Learningcited by 248
  5. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  6. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  7. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  8. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  9. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  10. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  11. 2022Synthetic Data -- what, why and how?cited by 66
  12. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
38 more
  1. 2022Debiased Self-Training for Semi-Supervised Learningcited by 62
  2. 2022BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotationcited by 54
  3. 2021CLDA: Contrastive Learning for Semi-Supervised Domain Adaptationcited by 52
  4. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  5. 2023Diffusion Models With Learned Adaptive Noisecited by 50
  6. 2021SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Trainingcited by 45
  7. 2024Memory Consolidation Enables Long-Context Video Understandingcited by 45
  8. 2023Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labelscited by 37
  9. 2021ECACL: A Holistic Framework for Semi-Supervised Domain Adaptationcited by 31
  10. 2022Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysiscited by 29
  11. 2023Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Networkcited by 28
  12. 2021Removing Undesirable Feature Contributions Using Out-of-Distribution Datacited by 23
  13. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  14. 2021Medical Image Segmentation with Limited Supervision: A Review of Deep Network Modelscited by 21
  15. 2024Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumventioncited by 21
  16. 2023Neural Diffusion Modelscited by 20
  17. 2023Pseudo-label Alignment for Semi-supervised Instance Segmentationcited by 17
  18. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  19. 2021Credal Self-Supervised Learningcited by 15
  20. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  21. 2023SemiReward: A General Reward Model for Semi-supervised Learningcited by 14
  22. 2021RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learningcited by 13
  23. 2022A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sourcescited by 13
  24. 2021Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbationscited by 12
  25. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  26. 2023Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approachcited by 10
  27. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  28. 2022RareGAN: Generating Samples for Rare Classescited by 9
  29. 2021Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approachcited by 8
  30. 2022Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Surveycited by 8
  31. 2024Mutual Information Guided Backdoor Mitigation for Pre-trained Encoderscited by 8
  32. 2021Probabilistic Contrastive Learning for Domain Adaptationcited by 7
  33. 2024Adversarial Training: A Surveycited by 6
  34. 2022Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completioncited by 5
  35. 2022Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentationcited by 5
  36. 2024Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detectioncited by 5
  37. 2022OSSGAN: Open-Set Semi-Supervised Image Generationcited by 4
  38. 2023Meta-DM: Applications of Diffusion Models on Few-Shot Learningcited by 4

50 most cited of 85 All 85 (JSON)