mlsanityData to 7 Oct 2026

Improved Input Reprogramming for GAN Conditioning

arXiv 2201.02692 ↗First posted 7 Jan 2022cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approaches to this problem -- conditional GAN training from scratch, fine-tuning, and input reprogramming. Our analysis reveals that when the amount of labeled data is small, input reprogramming performs the best. Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm. After identifying a few critical issues of the previous input reprogramming approach, we propose a new algorithm called InRep+. Our algorithm InRep+ addresses the existing issues with the novel uses of invertible neural networks and Positive-Unlabeled (PU) learning. Via extensive experiments, we show that InRep+ outperforms all existing methods, particularly when label information is scarce, noisy, and/or imbalanced. For instance, for the task of conditioning a CIFAR10 GAN with 1% labeled data, InRep+ achieves an average Intra-FID of 76.24, whereas the second-best method achieves 114.51.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 55 of its 84 references that are in the map. First posted on arXiv 7 Jan 2022.

Builds on

55 of 84 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2016Learning without Forgettingcited by 2,465
  11. 2014Conditional Generative Adversarial Netscited by 2,152
  12. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
38 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  2. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  5. 2019An Introduction to Variational Autoencoderscited by 997
  6. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  7. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  8. 2016Generative Adversarial Text to Image Synthesiscited by 735
  9. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  10. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
  11. 2018Invertible Residual Networkscited by 364
  12. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  13. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  14. 2018cGANs with Projection Discriminatorcited by 253
  15. 2017Geometric GANcited by 232
  16. 2016Adversarially Learned Inferencecited by 216
  17. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  18. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  19. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  20. 2018i-RevNet: Deep Invertible Networkscited by 137
  21. 2018Transferring GANs: generating images from limited datacited by 134
  22. 2019Classification Accuracy Score for Conditional Generative Modelscited by 134
  23. 2018Adversarial Reprogramming of Neural Networkscited by 115
  24. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  25. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
  26. 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91
  27. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  28. 2020Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resourcescited by 83
  29. 2018How good is my GAN?cited by 74
  30. 2021Controllable and Compositional Generation with Latent-Space Energy-Based Modelscited by 64
  31. 2020Diverse Image Generation via Self-Conditioned GANscited by 54
  32. 2019High-Fidelity Image Generation With Fewer Labelscited by 51
  33. 2017Learning From Noisy Singly-labeled Datacited by 50
  34. 2017Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Modelscited by 39
  35. 2019MintNet: Building Invertible Neural Networks with Masked Convolutionscited by 35
  36. 2019JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Videocited by 31
  37. 2018Robustness of Conditional GANs to Noisy Labelscited by 27
  38. 2020On Positive-Unlabeled Classification in GANcited by 14

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4.

7 papers.

  1. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  2. 2023The Expressive Power of Low-Rank Adaptationcited by 100
  3. 2022Model Reprogramming: Resource-Efficient Cross-Domain Machine Learningcited by 64
  4. 2023Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognitioncited by 13
  5. 2023Towards Efficient Task-Driven Model Reprogramming with Foundation Modelscited by 5
  6. 2022Meta Input: How to Leverage Off-the-Shelf Deep Neural Networkscited by 0
  7. 2023Large-Scale Public Data Improves Differentially Private Image Generation Qualitycited by 0