mlsanityData to 7 Oct 2026

On Noise Injection in Generative Adversarial Networks

arXiv 2006.05891 ↗First posted 10 Jun 2020cs.LG stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

Noise injection has been proved to be one of the key technique advances in generating high-fidelity images. Despite its successful usage in GANs, the mechanism of its validity is still unclear. In this paper, we propose a geometric framework to theoretically analyze the role of noise injection in GANs. Based on Riemannian geometry, we successfully model the noise injection framework as fuzzy equivalence on the geodesic normal coordinates. Guided by our theories, we find that the existing method is incomplete and a new strategy for noise injection is devised. Experiments on image generation and GAN inversion demonstrate the superiority of our method.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 6; 2023: 5; 2024: 4; 2025: 1.

19 papers.

Sort:

By area:

  1. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  2. 2022Rank Diminishing in Deep Neural Networkscited by 47
  3. 2023Diffusion Model-Augmented Behavioral Cloningcited by 37
  4. 2024Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environmentscited by 23
  5. 2023HairCLIPv2: Unifying Hair Editing via Proxy Feature Blendingcited by 17
  6. 2021Weakly Supervised High-Fidelity Clothing Model Generationcited by 9
  7. 2024Makeup Prior Models for 3D Facial Makeup Estimation and Applicationscited by 7
  8. 2022Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolutioncited by 6
  9. 2023Precise and Generalized Robustness Certification for Neural Networkscited by 4
  10. 2022Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulationcited by 3
  11. 2021Controlled GAN-Based Creature Synthesis via a Challenging Game Art Dataset -- Addressing the Noise-Latent Trade-Offcited by 2
  12. 2021Generative Adversarial Networks via a Composite Annealing of Noise and Diffusioncited by 1
7 more
  1. 2022Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Datacited by 1
  2. 2025Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversitycited by 1
  3. 2022Maximum Likelihood on the Joint (Data, Condition) Distribution for Solving Ill-Posed Problems with Conditional Flow Modelscited by 0
  4. 2022Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networkscited by 0
  5. 2023Defensive ML: Defending Architectural Side-channels with Adversarial Obfuscationcited by 0
  6. 2024Noise Dimension of GAN: An Image Compression Perspectivecited by 0
  7. 2024Scaling-based Data Augmentation for Generative Models and its Theoretical Extensioncited by 0