mlsanityData to 7 Oct 2026

On Self Modulation for Generative Adversarial Networks

arXiv 1810.01365 ↗First posted 2 Oct 2018cs.LG cs.CV stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

Training Generative Adversarial Networks (GANs) is notoriously challenging. We propose and study an architectural modification, self-modulation, which improves GAN performance across different data sets, architectures, losses, regularizers, and hyperparameter settings. Intuitively, self-modulation allows the intermediate feature maps of a generator to change as a function of the input noise vector. While reminiscent of other conditioning techniques, it requires no labeled data. In a large-scale empirical study we observe a relative decrease of 5%-35% in FID. Furthermore, all else being equal, adding this modification to the generator leads to improved performance in 124/144 (86%) of the studied settings. Self-modulation is a simple architectural change that requires no additional parameter tuning, which suggests that it can be applied readily to any GAN.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 8; 2023: 5; 2024: 3; 2025: 2; 2026: 1.

33 papers.

Sort:

By area:

  1. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  2. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  3. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  4. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  5. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 219
  6. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  7. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  8. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  9. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  10. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  11. 2023Modular Deep Learningcited by 82
  12. 2021Improved Transformer for High-Resolution GANscited by 59
21 more
  1. 2021Conditional Deformable Image Registration with Convolutional Neural Networkcited by 59
  2. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  3. 2024Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Modelscited by 31
  4. 2021Dual Contrastive Loss and Attention for GANscited by 30
  5. 2021Adaptive Denoising via GainTuningcited by 16
  6. 2022ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseasescited by 14
  7. 2021CoPE: Conditional image generation using Polynomial Expansionscited by 12
  8. 2023Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generationcited by 12
  9. 2021Self-Supervised GANs with Label Augmentationcited by 9
  10. 2025Hadamard product in deep learning: Introduction, Advances and Challengescited by 9
  11. 2022Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecastingcited by 7
  12. 2021Enhance Images as You Like with Unpaired Learningcited by 5
  13. 2023Coordinate-Aware Modulation for Neural Fieldscited by 4
  14. 2022Unveiling the Latent Space Geometry of Push-Forward Generative Modelscited by 3
  15. 2023Diverse Shape Completion via Style Modulated Generative Adversarial Networkscited by 2
  16. 2024Efficient generative adversarial networks using linear additive-attention Transformerscited by 2
  17. 2021Self Sparse Generative Adversarial Networkscited by 1
  18. 2025End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddingscited by 1
  19. 2021Unsupervised Image Transformation Learning via Generative Adversarial Networkscited by 0
  20. 2023Unlocking the Power of GANs in Non-Autoregressive Text Generationcited by 0
  21. 2026SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptationcited by 0