mlsanityData to 7 Oct 2026

MGGAN: Solving Mode Collapse using Manifold Guided Training

arXiv 1804.04391 ↗First posted 12 Apr 2018cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Mode collapse is a critical problem in training generative adversarial networks. To alleviate mode collapse, several recent studies introduce new objective functions, network architectures or alternative training schemes. However, their achievement is often the result of sacrificing the image quality. In this paper, we propose a new algorithm, namely a manifold guided generative adversarial network (MGGAN), which leverages a guidance network on existing GAN architecture to induce generator learning all modes of data distribution. Based on extensive evaluations, we show that our algorithm resolves mode collapse without losing image quality. In particular, we demonstrate that our algorithm is easily extendable to various existing GANs. Experimental analysis justifies that the proposed algorithm is an effective and efficient tool for training GANs.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

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

22 papers.

Sort:

By area:

  1. 2022Mildly Conservative Q-Learning for Offline Reinforcement Learningcited by 112
  2. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  3. 2022Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Valuescited by 21
  4. 2023Guiding Energy-based Models via Contrastive Latent Variablescited by 17
  5. 2022A survey on GANs for computer vision: Recent research, analysis and taxonomycited by 15
  6. 2023Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusioncited by 11
  7. 2024MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generationcited by 10
  8. 2021DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generationcited by 7
  9. 2024AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learningcited by 6
  10. 2022Single-level Adversarial Data Synthesis based on Neural Tangent Kernelscited by 2
  11. 2024CAS-GAN for Contrast-free Angiography Synthesiscited by 2
  12. 2024Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identificationcited by 2
10 more
  1. 2024On the Fairness, Diversity and Reliability of Text-to-Image Generative Modelscited by 2
  2. 2025FedBM: Stealing Knowledge from Pre-trained Language Models for Heterogeneous Federated Learningcited by 2
  3. 2025Text-to-3D Generation using Jensen-Shannon Score Distillationcited by 2
  4. 2021IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapsecited by 1
  5. 2021HGAN: Hybrid Generative Adversarial Networkcited by 0
  6. 2021SVMax: A Feature Embedding Regularizercited by 0
  7. 2021VARGAN: Variance Enforcing Network Enhanced GANcited by 0
  8. 2022Hierarchical Vectorization for Portrait Imagescited by 0
  9. 2022Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networkscited by 0
  10. 2026Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generationcited by 0