Publications (13)
Construct Informative Triplet with Two-stage Hard-sample Generation
Chuang Zhu, Zheng Hu, Huihui Dong +3
In this paper, we propose a robust sample generation scheme to construct informative triplets. The proposed hard sample generation is a two-stage synthesis framework that produces…
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
Mengwen Ye, Yingzi Huangfu, Shujian Gao +3
Federated Learning (FL) emerged as a solution for collaborative medical image classification while preserving data privacy. However, label noise, which arises from inter-institutio…
RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT
Chuyu Zhao, Hao Huang, Jiashuo Guo +4
Semi-supervised learning has become a compelling approach for 3D tooth segmentation from CBCT scans, where labeled data is minimal. However, existing methods still face two persist…
Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review
Chuang Zhu, Shengjie Liu, Zekuan Yu +15
For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in breast tissue t…
PML: Progressive Margin Loss for Long-tailed Age Classification
Zongyong Deng, Hao Liu, Yaoxing Wang +3
In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification. Conventional methods make strong assumption on that each class owns…
BARL: Bilateral Alignment in Representation and Label Spaces for Semi-Supervised Volumetric Medical Image Segmentation
Shujian Gao, Yuan Wang, Zekuan Yu
Semi-supervised medical image segmentation (SSMIS) seeks to match fully supervised performance while sharply reducing annotation cost. Mainstream SSMIS methods rely on \emph{label-…
SSHNN: Semi-Supervised Hybrid NAS Network for Echocardiographic Image Segmentation
Renqi Chen, Jingjing Luo, Fan Nian +3
Accurate medical image segmentation especially for echocardiographic images with unmissable noise requires elaborate network design. Compared with manual design, Neural Architectur…
Open-Access Data and Toolbox for Tracking COVID-19 Impact on Power Systems
Guangchun Ruan, Zekuan Yu, Shutong Pu +5
Intervention policies against COVID-19 have caused large-scale disruptions globally, and led to a series of pattern changes in the power system operation. Analyzing these pandemic-…
SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Loss
Mengwen Ye, Yingzi Huangfu, You Li +1
Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challen…
Registration-Free Hybrid Learning Empowers Simple Multimodal Imaging System for High-quality Fusion Detection
Yinghan Guan, Haoran Dai, Zekuan Yu +2
Multimodal fusion detection always places high demands on the imaging system and image pre-processing, while either a high-quality pre-registration system or image registration pro…
Network-Constrained Unit Commitment with Flexible Temporal Resolution
Zekuan Yu, Haiwang Zhong, Guangchun Ruan +1
Modern network-constrained unit commitment (NCUC) bears a heavy computational burden due to the ever-growing model scale. This situation becomes more challenging when detailed oper…
Look-Ahead AC Optimal Power Flow: A Model-Informed Reinforcement Learning Approach
Xinyue Wang, Haiwang Zhong, Guanglun Zhang +3
With the increasing proportion of renewable energy in the generation side, it becomes more difficult to accurately predict the power generation and adapt to the large deviations be…
Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning
Zekuan Yu, Guangchun Ruan, Xinyue Wang +3
Modern power systems are experiencing a variety of challenges driven by renewable energy, which calls for developing novel dispatch methods such as reinforcement learning (RL). Eva…