mlsanityData to 14 Oct 2026

ABCAS: Adaptive Bound Control of spectral norm as Automatic Stabilizer

arXiv 2211.06595 ↗First posted 12 Nov 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Spectral Normalization is one of the best methods for stabilizing the training of Generative Adversarial Network. Spectral Normalization limits the gradient of discriminator between the distribution between real data and fake data. However, even with this normalization, GAN's training sometimes fails. In this paper, we reveal that more severe restriction is sometimes needed depending on the training dataset, then we propose a novel stabilizer which offers an adaptive normalization method, called ABCAS. Our method decides discriminator's Lipschitz constant adaptively, by checking the distance of distributions of real and fake data. Our method improves the stability of the training of Generative Adversarial Network and achieved better Fr'echet Inception Distance score of generated images. We also investigated suitable spectral norm for three datasets. We show the result as an ablation study.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 19 references that are in the map. First posted on arXiv 12 Nov 2022.

Builds on

15 of 19 references.

References · 15

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  8. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  9. 2016Least Squares Generative Adversarial Networkscited by 1,001
  10. 2018Self-Attention Generative Adversarial Networkscited by 809
  11. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  12. 2017Spectral Norm Regularization for Improving the Generalizability of Deep Learningcited by 182
3 more
  1. 2016Energy-based Generative Adversarial Networkcited by 119
  2. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  3. 2021Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learningcited by 25

Built on by

Not cited yet.