Machine learning methods for small data challenges in molecular science

B Dou, Z Zhu, E Merkurjev, L Ke, L Chen… - Chemical …, 2023‏ - ACS Publications
Small data are often used in scientific and engineering research due to the presence of
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …

Generative adversarial networks (GANs) challenges, solutions, and future directions

D Saxena, J Cao - ACM Computing Surveys (CSUR), 2021‏ - dl.acm.org
Generative Adversarial Networks (GANs) is a novel class of deep generative models that
has recently gained significant attention. GANs learn complex and high-dimensional …

Imperfect ImaGANation: Implications of GANs exacerbating biases on facial data augmentation and snapchat face lenses

N Jain, A Olmo, S Sengupta, L Manikonda… - Artificial Intelligence, 2022‏ - Elsevier
In this paper, we show that popular Generative Adversarial Network (GAN) variants
exacerbate biases along the axes of gender and skin tone in the generated data. The use of …

MASCDB, a database of images, descriptors and microphysical properties of individual snowflakes in free fall

J Grazioli, G Ghiggi, AC Billault-Roux, A Berne - Scientific data, 2022‏ - nature.com
Snowfall information at the scale of individual particles is rare, difficult to gather, but
fundamental for a better understanding of solid precipitation microphysics. In this article we …

Improving generative adversarial networks via adversarial learning in latent space

Y Li, Y Mo, L Shi, J Yan - Advances in neural information …, 2022‏ - proceedings.neurips.cc
Abstract For Generative Adversarial Networks which map a latent distribution to the target
distribution, in this paper, we study how the sampling in latent space can affect the …

Improving clustergan using self-augmented information maximization of disentangling latent spaces

T Dam, SG Anavatti, HA Abbass - arxiv preprint arxiv:2107.12706, 2021‏ - arxiv.org
Since their introduction in the last few years, conditional generative models have seen
remarkable achievements. However, they often need the use of large amounts of labelled …

Searching towards class-aware generators for conditional generative adversarial networks

P Zhou, L **e, B Ni, Q Tian - IEEE Signal Processing Letters, 2022‏ - ieeexplore.ieee.org
Conditional generative adversarial networks (cGANs) are designed to generate images
based on the provided conditions, eg., class-level distributions, semantic label maps, etc …

Self-supervised augmentation of quality data based on classification-reinforced GAN

SH Kim, S Lee - 2023 17th International Conference on …, 2023‏ - ieeexplore.ieee.org
In deep learning, the quality of ground truth training data is crucial for the resulting
performance. However, depending on applications, collecting a sufficient amount of quality …

Survey of generative adversarial network.

W Zhenglong, Z BaoWen - Chinese Journal of Network & …, 2021‏ - search.ebscohost.com
Firstly, the basic theory, application scenarios and current state of research of GAN
(generative adversarial network) were introduced, and the problems need to be improved …

Sequence Modeling Based Data Augmentation for Micro-expression Recognition

X Lin, S Ai, J Gao, J He, L Yan, J Zhang… - International Forum on …, 2023‏ - Springer
Micro-expressions (MEs) can reveal people's true emotions and expose deceitful behaviors.
With the introduction of deep learning, the accuracy of micro-expression recognition (MER) …