Generalizing to unseen domains: A survey on domain generalization

J Wang, C Lan, C Liu, Y Ouyang, T Qin… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Trustworthy representation learning across domains

R Zhu, D Guo, D Qi, Z Chu, X Yu, S Li - arXiv preprint arXiv:2308.12315, 2023 - arxiv.org
As AI systems have obtained significant performance to be deployed widely in our daily live
and human society, people both enjoy the benefits brought by these technologies and suffer …

A Survey of Trustworthy Representation Learning Across Domains

R Zhu, D Guo, D Qi, Z Chu, X Yu, S Li - ACM Transactions on …, 2024 - dl.acm.org
As AI systems have obtained significant performance to be deployed widely in our daily live
and human society, people both enjoy the benefits brought by these technologies and suffer …

Subsidiary prototype alignment for universal domain adaptation

JN Kundu, S Bhambri, AR Kulkarni… - Advances in …, 2022 - proceedings.neurips.cc
Abstract Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer
between two datasets with domain-shift as well as category-shift. The goal is to categorize …

Agi for agriculture

G Lu, S Li, G Mai, J Sun, D Zhu, L Chai, H Sun… - arXiv preprint arXiv …, 2023 - arxiv.org
Artificial General Intelligence (AGI) is poised to revolutionize a variety of sectors, including
healthcare, finance, transportation, and education. Within healthcare, AGI is being utilized to …

Cross-domain graph convolutions for adversarial unsupervised domain adaptation

R Zhu, X Jiang, J Lu, S Li - IEEE Transactions on Neural …, 2021 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) has attracted increasing attention in recent years,
which adapts classifiers to an unlabeled target domain by exploiting a labeled source …

Universal domain adaptive network embedding for node classification

J Chen, F Dai, X Gu, J Zhou, B Li, W Wang - Proceedings of the 31st …, 2023 - dl.acm.org
Cross-network node classification aims to leverage the abundant knowledge from a labeled
source network to help classify the node in an unlabeled target network. However, existing …

From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation

R Wen, H Yuan, D Ni, W Xiao… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
In medical image segmentation, domain generalization poses a significant challenge due to
domain shifts caused by variations in data acquisition devices and other factors. These shifts …

Pairwise adversarial training for unsupervised class-imbalanced domain adaptation

W Shi, R Zhu, S Li - Proceedings of the 28th ACM SIGKDD conference …, 2022 - dl.acm.org
Unsupervised domain adaptation (UDA) has become an appealing approach for knowledge
transfer from a labeled source domain to an unlabeled target domain. However, when the …

Progressive mix-up for few-shot supervised multi-source domain transfer

R Zhu, X Yu, S Li - The eleventh international conference on …, 2023 - openreview.net
This paper targets at a new and challenging setting of knowledge transfer from multiple
source domains to a single target domain, where target data is few shot or even one shot …