paper-with-me

홈 › Papers

MMCGAN: Generative Adversarial Network with Explicit Manifold Prior

2020-06-18 · Guanhua Zheng, Jitao Sang, Changsheng Xu

Generative Adversarial Network(GAN) provides a good generative framework to produce realistic samples, but suffers from two recognized issues as mode collapse and unstable training. In this work, we propose to employ explicit manifold learning as prior to alleviate mode collapse and stabilize training of GAN. Since the basic assumption of conventional manifold learning fails in case of sparse and uneven data distribution, we introduce a new target, Minimum Manifold Coding (MMC), for manifold learning to encourage simple and unfolded manifold. In essence, MMC is the general case of the shortest Hamiltonian Path problem and pursues manifold with minimum Riemann volume. Using the standardized code from MMC as prior, GAN is guaranteed to recover a simple and unfolded manifold covering all the training data. Our experiments on both the toy data and real datasets show the effectiveness of MMCGAN in alleviating mode collapse, stabilizing training, and improving the quality of generated samples.

📄 PDF Abstract BibTeX arXiv:2006.10331

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial Network

Similar Papers 제목 키워드 기반

Generative Model Inversion Through the Lens of the Manifold Hypothesis

2025-09-24 · Xiong Peng, Bo Han, Fengfei Yu, Tongliang Liu 외 arxiv

Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models. Recent generative MIAs utilize generative adversarial networks to learn image priors that guide the inversion process, y…

Generating and Aligning from Data Geometries with Generative Adversarial Networks

2019-01-24 · Matthew Amodio, Smita Krishnaswamy

Unsupervised domain mapping has attracted substantial attention in recent years due to the success of models based on the cycle-consistency assumption. These models map between two domains by fooling a probabilistic disc…

Generative Adversarial Network

Disconnected Manifold Learning for Generative Adversarial Networks

2018-06-03 · NeurIPS 2018 12 · Mahyar Khayatkhoei, Ahmed Elgammal, Maneesh Singh

Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work…

A Non-Adversarial Approach to Idempotent Generative Modelling

2025-11-04 · Mohammed Al-Jaff, Giovanni Luca Marchetti, Michael C Welle, Jens Lundell 외 arxiv

Idempotent Generative Networks (IGNs) are deep generative models that also function as local data manifold projectors, mapping arbitrary inputs back onto the manifold. They are trained to act as identity operators on the…

Disentangling Adversarial Robustness in Directions of the Data Manifold

2021-01-01 · Jiancong Xiao, Liusha Yang, Zhi-Quan Luo

Using generative models (GAN or VAE) to craft adversarial examples, i.e. generative adversarial examples, has received increasing attention in recent years. Previous studies showed through experiments that the generative…

Adversarial Robustness