English
Related papers

Related papers: A black box for dark sector physics: Predicting da…

200 papers

Adapting to the changing climate requires accurate local climate information, a computationally challenging problem. Recent studies have used Generative Adversarial Networks (GANs), a type of deep learning, to learn complex distributions…

Machine Learning · Computer Science 2024-06-06 Kiri Daust , Adam Monahan

Generative Adversarial Networks (GANs) are a recent advancement in unsupervised machine learning. They are a cat-and-mouse game between two neural networks: [1] a discriminator network which learns to validate whether a sample is real or…

Cosmology and Nongalactic Astrophysics · Physics 2020-06-23 Olivia Curtis , Tereasa G. Brainerd

Although active galactic nuclei (AGN) feedback is required in simulations of galaxies to regulate star formation, further downstream effects on the dark matter distribution of the halo and stellar kinematics of the central galaxy can be…

Feedback processes are thought to solve some of the long-standing issues of the numerical modelling of galaxy formation: over-cooling, low angular momentum, massive blue galaxies, extra-galactic enrichment, etc. The accretion of gas onto…

Cosmology and Nongalactic Astrophysics · Physics 2011-09-08 Yohan Dubois , Julien Devriendt , Adrianne Slyz , Romain Teyssier

Generative Adversarial Networks (GANs) have facilitated a new direction to tackle the image-to-image transformation problem. Different GANs use generator and discriminator networks with different losses in the objective function. Still…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Kancharagunta Kishan Babu , Shiv Ram Dubey

Accurate surface roughness prediction in ultra-precision machining (UPM) is critical for real-time quality control, but small datasets hinder model performance. We propose HAS-CGAN, a Hybrid Adversarial Spectral Loss CGAN, for effective UPM…

Machine Learning · Computer Science 2025-07-08 Suiyan Shang , Chi Fai Cheung , Pai Zheng

In this work we demonstrate that generative adversarial networks (GANs) can be used to generate realistic pervasive changes in remote sensing imagery, even in an unpaired training setting. We investigate some transformation quality metrics…

Image and Video Processing · Electrical Eng. & Systems 2020-05-19 Christopher X. Ren , Amanda Ziemann , James Theiler , Alice M. S. Durieux

A Generative Adversarial Network (GAN) was used to investigate the statistics and properties of voids in a $\Lambda$CDMuniverse. The total number of voids and the distribution of void sizes is similar in both sets of images and, within the…

Cosmology and Nongalactic Astrophysics · Physics 2021-11-22 Olivia Curtis , Tereasa Brainerd , Anthony Hernandez

Generative Adversarial Networks (GANs) are a well-known technique that is trained on samples (e.g. pictures of fruits) and which after training is able to generate realistic new samples. Conditional GANs (CGANs) additionally provide label…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Maximilian Bachl , Daniel C. Ferreira

Over the past years, Generative Adversarial Networks (GANs) have shown a remarkable generation performance especially in image synthesis. Unfortunately, they are also known for having an unstable training process and might loose parts of…

Machine Learning · Computer Science 2019-11-18 Teodora Pandeva , Matthias Schubert

Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major…

Machine Learning · Computer Science 2018-11-05 Zinan Lin , Ashish Khetan , Giulia Fanti , Sewoong Oh

In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them. Different…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Lingyun Jiang , Kai Qiao , Ruoxi Qin , Linyuan Wang , Jian Chen , Haibing Bu , Bin Yan

Recent advances in conditional generative modeling have introduced Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM) for estimating high-dimensional data distributions…

Machine Learning · Computer Science 2026-02-04 Xin Ding , Yun Chen , Yongwei Wang , Kao Zhang , Sen Zhang , Peibei Cao , Xiangxue Wang

Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks. We introduce a simple yet effective approach…

Machine Learning · Computer Science 2019-10-22 Sangwoo Mo , Chiheon Kim , Sungwoong Kim , Minsu Cho , Jinwoo Shin

Obtaining truly representative pore-scale images that match bulk formation properties remains a fundamental challenge in subsurface characterization, as natural spatial heterogeneity causes extracted sub-images to deviate significantly from…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Ali Sadeghkhani , Brandon Bennett , Masoud Babaei , Arash Rabbani

We introduce Kernel Density Discrimination GAN (KDD GAN), a novel method for generative adversarial learning. KDD GAN formulates the training as a likelihood ratio optimization problem where the data distributions are written explicitly via…

Machine Learning · Computer Science 2021-07-14 Abdelhak Lemkhenter , Adam Bielski , Alp Eren Sari , Paolo Favaro

Active galactic nuclei (AGN) have been observed in dwarf galaxies, yet the impact of black hole feedback in these low-mass systems remains unclear. To uncover the potential effects of AGN in the low-mass galaxy regime, we study the…

Generative Adversarial Networks (GANs) have shown remarkable results in modeling complex distributions, but their evaluation remains an unsettled issue. Evaluations are essential for: (i) relative assessment of different models and (ii)…

We show that the impact of energy injection by dark matter annihilation on the cosmic microwave background power spectra can be apprehended via a residual likelihood map. By resorting to convolutional neural networks that can fully discover…

Cosmology and Nongalactic Astrophysics · Physics 2021-06-23 Wei-Chih Huang , Jui-Lin Kuo , Yue-Lin Sming Tsai

We develop a transformer-based conditional generative model for discrete point objects and their properties. We use it to build a model for populating cosmological simulations with gravitationally collapsed structures called dark matter…

Cosmology and Nongalactic Astrophysics · Physics 2024-09-18 Shivam Pandey , Francois Lanusse , Chirag Modi , Benjamin D. Wandelt