88 citations · 278 across the 11 of their papers we have counts for
11 papers
Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks
Kaixin Xu, Zhe Wang, Xue Geng +4
In this paper, we propose a novel layer-adaptive weight-pruning approach for Deep Neural Networks (DNNs) that addresses the challenge of optimizing the output distortion minimizati…
GaitFormer: Revisiting Intrinsic Periodicity for Gait Recognition
Qian Wu, Ruixuan Xiao, Kaixin Xu +3
Gait recognition aims to distinguish different walking patterns by analyzing video-level human silhouettes, rather than relying on appearance information. Previous research on gait…
MS-MT: Multi-Scale Mean Teacher with Contrastive Unpaired Translation for Cross-Modality Vestibular Schwannoma and Cochlea Segmentation
Ziyuan Zhao, Kaixin Xu, Huai Zhe Yeo +2
Domain shift has been a long-standing issue for medical image segmentation. Recently, unsupervised domain adaptation (UDA) methods have achieved promising cross-modality segmentati…
MetaGrad: Adaptive Gradient Quantization with Hypernetworks
Kaixin Xu, Alina Hui Xiu Lee, Ziyuan Zhao +3
A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference. However,…
LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation
Ziyuan Zhao, Fangcheng Zhou, Kaixin Xu +3
While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-…
Self-supervised Assisted Active Learning for Skin Lesion Segmentation
Ziyuan Zhao, Wenjing Lu, Zeng Zeng +3
Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements. Recently, active learning (AL) strategi…
Object-Aware Self-supervised Multi-Label Learning
Xu Kaixin, Liu Liyang, Zhao Ziyuan +2
Multi-label Learning on Image data has been widely exploited with deep learning models. However, supervised training on deep CNN models often cannot discover sufficient discriminat…
MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels
Ziyuan Zhao, Kaixin Xu, Shumeng Li +2
The success of deep convolutional neural networks (DCNNs) benefits from high volumes of annotated data. However, annotating medical images is laborious, expensive, and requires hum…
Hierarchical Consistency Regularized Mean Teacher for Semi-supervised 3D Left Atrium Segmentation
Shumeng Li, Ziyuan Zhao, Kaixin Xu +2
Deep learning has achieved promising segmentation performance on 3D left atrium MR images. However, annotations for segmentation tasks are expensive, costly and difficult to obtain…
DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation
Ziyuan Zhao, Zeng Zeng, Kaixin Xu +2
Image segmentation is one of the most essential biomedical image processing problems for different imaging modalities, including microscopy and X-ray in the Internet-of-Medical-Thi…
Multi-Instance Multi-Label Learning for Gene Mutation Prediction in Hepatocellular Carcinoma
Kaixin Xu, Ziyuan Zhao, Jiapan Gu +5
Gene mutation prediction in hepatocellular carcinoma (HCC) is of great diagnostic and prognostic value for personalized treatments and precision medicine. In this paper, we tackle…