Instance-conditioned gan

A Casanova, M Careil, J Verbeek… - Advances in …, 2021 - proceedings.neurips.cc
Abstract Generative Adversarial Networks (GANs) can generate near photo realistic images
in narrow domains such as human faces. Yet, modeling complex distributions of datasets …

Semi-supervised vision transformers at scale

Z Cai, A Ravichandran, P Favaro… - Advances in …, 2022 - proceedings.neurips.cc
We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored
topic despite the wide adoption of the ViT architectures to different tasks. To tackle this …

Improving generalization and stability of generative adversarial networks

H Thanh-Tung, T Tran, S Venkatesh - arxiv preprint arxiv:1902.03984, 2019 - arxiv.org
Generative Adversarial Networks (GANs) are one of the most popular tools for learning
complex high dimensional distributions. However, generalization properties of GANs have …

Creating artificial human genomes using generative neural networks

B Yelmen, A Decelle, L Ongaro, D Marnetto… - PLoS …, 2021 - journals.plos.org
Generative models have shown breakthroughs in a wide spectrum of domains due to recent
advancements in machine learning algorithms and increased computational power. Despite …

Interpolation-based contrastive learning for few-label semi-supervised learning

X Yang, X Hu, S Zhou, X Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Semi-supervised learning (SSL) has long been proved to be an effective technique to
construct powerful models with limited labels. In the existing literature, consistency …

Deep learning for population size history inference: Design, comparison and combination with approximate Bayesian computation

T Sanchez, J Cury, G Charpiat… - Molecular Ecology …, 2021 - Wiley Online Library
For the past decades, simulation‐based likelihood‐free inference methods have enabled
researchers to address numerous population genetics problems. As the richness and …

Unsupervised CT metal artifact learning using attention-guided β-CycleGAN

J Lee, J Gu, JC Ye - IEEE Transactions on Medical Imaging, 2021 - ieeexplore.ieee.org
Metal artifact reduction (MAR) is one of the most important research topics in computed
tomography (CT). With the advance of deep learning approaches for image reconstruction …

Mixed graph contrastive network for semi-supervised node classification

X Yang, Y Wang, Y Liu, Y Wen, L Meng… - ACM Transactions on …, 2024 - dl.acm.org
Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised
node classification in recent years. However, the problem of insufficient supervision …

Gdpp: Learning diverse generations using determinantal point processes

M Elfeki, C Couprie, M Riviere… - … on machine learning, 2019 - proceedings.mlr.press
Generative models have proven to be an outstanding tool for representing high-dimensional
probability distributions and generating realistic looking images. An essential characteristic …

A simple baseline algorithm for graph classification

N de Lara, E Pineau - arxiv preprint arxiv:1810.09155, 2018 - arxiv.org
Graph classification has recently received a lot of attention from various fields of machine
learning eg kernel methods, sequential modeling or graph embedding. All these …