mlsanityData to 7 Oct 2026

Spectral Regularization for Combating Mode Collapse in GANs

arXiv 1908.10999 ↗First posted 29 Aug 2019cs.LG stat.MLcited by 31

Not on the map. Why?

Abstract (arXiv)

Despite excellent progress in recent years, mode collapse remains a major unsolved problem in generative adversarial networks (GANs).In this paper, we present spectral regularization for GANs (SR-GANs), a new and robust method for combating the mode collapse problem in GANs. Theoretical analysis shows that the optimal solution to the discriminator has a strong relationship to the spectral distributions of the weight matrix.Therefore, we monitor the spectral distribution in the discriminator of spectral normalized GANs (SN-GANs), and discover a phenomenon which we refer to as spectral collapse, where a large number of singular values of the weight matrices drop dramatically when mode collapse occurs. We show that there are strong evidence linking mode collapse to spectral collapse; and based on this link, we set out to tackle spectral collapse as a surrogate of mode collapse. We have developed a spectral regularization method where we compensate the spectral distributions of the weight matrices to prevent them from collapsing, which in turn successfully prevents mode collapse in GANs. We provide theoretical explanations for why SR-GANs are more stable and can provide better performances than SN-GANs. We also present extensive experimental results and analysis to show that SR-GANs not only always outperform SN-GANs but also always succeed in combating mode collapse where SN-GANs fail. The code is available at https://github.com/max-liu-112/SRGANs-Spectral-Regularization-GANs-.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 7; 2024: 5; 2025: 1; 2026: 2.

31 papers.

Sort:

By area:

  1. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  2. 2021Gradient Normalization for Generative Adversarial Networkscited by 25
  3. 2022Underwater Light Field Retention : Neural Rendering for Underwater Imagingcited by 22
  4. 2022GLaMa: Joint Spatial and Frequency Loss for General Image Inpaintingcited by 15
  5. 2021A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for Efficient Hyperspectral Image Super-resolutioncited by 14
  6. 2021Manifold Learning Benefits GANscited by 14
  7. 2022Improving GANs for Long-Tailed Data through Group Spectral Regularizationcited by 14
  8. 2022Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIVcited by 12
  9. 2023Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusioncited by 11
  10. 2022Towards Practical Control of Singular Values of Convolutional Layerscited by 9
  11. 2023Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Modelscited by 9
  12. 2023Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learningcited by 9
19 more
  1. 2024Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpaintingcited by 9
  2. 2021DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generationcited by 7
  3. 2021Spectral Tensor Train Parameterization of Deep Learning Layerscited by 6
  4. 2021Optimal Latent Vector Alignment for Unsupervised Domain Adaptation in Medical Image Segmentationcited by 2
  5. 2022Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Rendererscited by 2
  6. 2023OrthoReg: Improving Graph-regularized MLPs via Orthogonality Regularizationcited by 2
  7. 2023Incomplete Multi-view Clustering via Diffusion Completioncited by 2
  8. 2024ComFusion: Personalized Subject Generation in Multiple Specific Scenes From Single Imagecited by 2
  9. 2024CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalizationcited by 2
  10. 2025LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generationcited by 2
  11. 2023Qualitative Data Augmentation for Performance Prediction in VLSI circuitscited by 1
  12. 2024Deep Learning based Optical Image Super-Resolution via Generative Diffusion Models for Layerwise in-situ LPBF Monitoringcited by 1
  13. 2021VARGAN: Variance Enforcing Network Enhanced GANcited by 0
  14. 2021SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoderscited by 0
  15. 2022Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networkscited by 0
  16. 2023Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flowcited by 0
  17. 2024High-Resolution Image Translation Model Based on Grayscale Redefinitioncited by 0
  18. 2026The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenderscited by 0
  19. 2026Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillationcited by 0