Mirrorgan: Learning text-to-image generation by redescription

T Qiao, J Zhang, D Xu, D Tao - Proceedings of the IEEE …, 2019‏ - openaccess.thecvf.com
Generating an image from a given text description has two goals: visual realism and
semantic consistency. Although significant progress has been made in generating high …

Unsupervised domain adaptation via structurally regularized deep clustering

H Tang, K Chen, K Jia - … of the IEEE/CVF conference on …, 2020‏ - openaccess.thecvf.com
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data on a
target domain, given labeled data on a source domain whose distribution shifts from the …

Discriminative adversarial domain adaptation

H Tang, K Jia - Proceedings of the AAAI conference on artificial …, 2020‏ - aaai.org
Given labeled instances on a source domain and unlabeled ones on a target domain,
unsupervised domain adaptation aims to learn a task classifier that can well classify target …

Deep visual unsupervised domain adaptation for classification tasks: a survey

Y Madadi, V Seydi, K Nasrollahi… - IET Image …, 2020‏ - Wiley Online Library
Learning methods are challenged when there is not enough labelled data. It gets worse
when the existing learning data have different distributions in different domains. To deal with …

Cross-domain facial expression recognition: A unified evaluation benchmark and adversarial graph learning

T Chen, T Pu, H Wu, Y **e, L Liu… - IEEE transactions on …, 2021‏ - ieeexplore.ieee.org
Facial expression recognition (FER) has received significant attention in the past decade
with witnessed progress, but data inconsistencies among different FER datasets greatly …

Time series domain adaptation via sparse associative structure alignment

R Cai, J Chen, Z Li, W Chen, K Zhang, J Ye… - Proceedings of the …, 2021‏ - ojs.aaai.org
Abstract Domain adaptation on time series data is an important but challenging task. Most of
the existing works in this area are based on the learning of the domain-invariant …

Unsupervised instance segmentation in microscopy images via panoptic domain adaptation and task re-weighting

D Liu, D Zhang, Y Song, F Zhang… - Proceedings of the …, 2020‏ - openaccess.thecvf.com
Unsupervised domain adaptation (UDA) for nuclei instance segmentation is important for
digital pathology, as it alleviates the burden of labor-intensive annotation and domain shift …

Federated domain adaptation via transformer for multi-site Alzheimer's disease diagnosis

B Lei, Y Zhu, E Liang, P Yang, S Chen… - … on Medical Imaging, 2023‏ - ieeexplore.ieee.org
In multi-site studies of Alzheimer's disease (AD), the difference of data in multi-site datasets
leads to the degraded performance of models in the target sites. The traditional domain …

Multi-source contribution learning for domain adaptation

K Li, J Lu, H Zuo, G Zhang - IEEE Transactions on Neural …, 2021‏ - ieeexplore.ieee.org
Transfer learning becomes an attractive technology to tackle a task from a target domain by
leveraging previously acquired knowledge from a similar domain (source domain). Many …

Feature-aware adaptation and density alignment for crowd counting in video surveillance

J Gao, Y Yuan, Q Wang - IEEE transactions on cybernetics, 2020‏ - ieeexplore.ieee.org
With the development of deep neural networks, the performance of crowd counting and pixel-
wise density estimation is continually being refreshed. Despite this, there are still two …