no code implementations • 17 Mar 2022 • Runqi Wang, Linlin Yang, Baochang Zhang, Wentao Zhu, David Doermann, Guodong Guo
Research on the generalization ability of deep neural networks (DNNs) has recently attracted a great deal of attention.
no code implementations • 26 Feb 2022 • Wentao Zhu, Hang Shang, Tingxun Lv, Chao Liao, Sen yang, Ji Liu
Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention.
no code implementations • 28 Dec 2021 • Runqi Wang, Xiaoyue Duan, Baochang Zhang, Song Xue, Wentao Zhu, David Doermann, Guodong Guo
We show that our method improves the recognition accuracy of adversarial training on ImageNet by 8. 32% compared with the baseline.
no code implementations • 19 Dec 2021 • Wentao Zhu, Zhuoqian Yang, Ziang Di, Wayne Wu, Yizhou Wang, Chen Change Loy
Trained with the canonicalization operations and the derived regularizations, our method learns to factorize a skeleton sequence into three independent semantic subspaces, i. e., motion, structure, and view angle.
1 code implementation • 15 Dec 2021 • Shuwei Shao, Zhongcai Pei, Weihai Chen, Wentao Zhu, Xingming Wu, Dianmin Sun, Baochang Zhang
Recently, self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in autonomous driving scenarios.
no code implementations • 16 Nov 2021 • Shuwei Shao, Ran Li, Zhongcai Pei, Zhong Liu, Weihai Chen, Wentao Zhu, Xingming Wu, Baochang Zhang
In particular, our method improves previous state-of-the-art methods from 0. 365 to 0. 349 on the metric RMSE on the NYU dataset.
1 code implementation • 15 Oct 2021 • Tianli Zhao, Xi Sheryl Zhang, Wentao Zhu, Jiaxing Wang, Sen yang, Ji Liu, Jian Cheng
In this paper, we present a unified framework with Joint Channel pruning and Weight pruning (JCW), and achieves a better Pareto-frontier between the latency and accuracy than previous model compression approaches.
1 code implementation • 18 Sep 2021 • Wentao Zhu, Tianlong Kong, Shun Lu, Jixiang Li, Dawei Zhang, Feng Deng, Xiaorui Wang, Sen yang, Ji Liu
Recently, x-vector has been a successful and popular approach for speaker verification, which employs a time delay neural network (TDNN) and statistics pooling to extract speaker characterizing embedding from variable-length utterances.
no code implementations • NeurIPS 2021 • Xuefan Zha, Wentao Zhu, Tingxun Lv, Sen yang, Ji Liu
However, the pure-Transformer based spatio-temporal learning can be prohibitively costly on memory and computation to extract fine-grained features from a tiny patch.
no code implementations • 16 Jul 2021 • Holger R. Roth, Dong Yang, Wenqi Li, Andriy Myronenko, Wentao Zhu, Ziyue Xu, Xiaosong Wang, Daguang Xu
Building robust deep learning-based models requires diverse training data, ideally from several sources.
no code implementations • 25 Mar 2021 • Wentao Zhu, Yufang Huang, Daguang Xu, Zhen Qian, Wei Fan, Xiaohui Xie
Registration is a fundamental task in medical robotics and is often a crucial step for many downstream tasks such as motion analysis, intra-operative tracking and image segmentation.
no code implementations • 7 Dec 2020 • Xuan Gong, Xin Xia, Wentao Zhu, Baochang Zhang, David Doermann, Lian Zhuo
In recent years, deep learning has dominated progress in the field of medical image analysis.
no code implementations • 23 Nov 2020 • Dong Yang, Ziyue Xu, Wenqi Li, Andriy Myronenko, Holger R. Roth, Stephanie Harmon, Sheng Xu, Baris Turkbey, Evrim Turkbey, Xiaosong Wang, Wentao Zhu, Gianpaolo Carrafiello, Francesca Patella, Maurizio Cariati, Hirofumi Obinata, Hitoshi Mori, Kaku Tamura, Peng An, Bradford J. Wood, Daguang Xu
To facilitate CT analysis, recent efforts have focused on computer-aided characterization and diagnosis, which has shown promising results.
no code implementations • COLING 2020 • Yufang Huang, Wentao Zhu, Deyi Xiong, Yiye Zhang, Changjian Hu, Feiyu Xu
Unsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation.
no code implementations • 10 Jul 2020 • Liyue Shen, Wentao Zhu, Xiaosong Wang, Lei Xing, John M. Pauly, Baris Turkbey, Stephanie Anne Harmon, Thomas Hogue Sanford, Sherif Mehralivand, Peter Choyke, Bradford Wood, Daguang Xu
Multi-domain data are widely leveraged in vision applications taking advantage of complementary information from different modalities, e. g., brain tumor segmentation from multi-parametric magnetic resonance imaging (MRI).
no code implementations • 22 Jun 2020 • Xiahai Zhuang, Jiahang Xu, Xinzhe Luo, Chen Chen, Cheng Ouyang, Daniel Rueckert, Victor M. Campello, Karim Lekadir, Sulaiman Vesal, Nishant Ravikumar, Yashu Liu, Gongning Luo, Jingkun Chen, Hongwei Li, Buntheng Ly, Maxime Sermesant, Holger Roth, Wentao Zhu, Jiexiang Wang, Xinghao Ding, Xinyue Wang, Sen yang, Lei LI
In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR.
1 code implementation • 22 Jun 2020 • Wentao Zhu, Can Zhao, Wenqi Li, Holger Roth, Ziyue Xu, Daguang Xu
In this work, we introduce Large deep 3D ConvNets with Automated Model Parallelism (LAMP) and investigate the impact of both input's and deep 3D ConvNets' size on segmentation accuracy.
no code implementations • CVPR 2020 • Zhuoqian Yang, Wentao Zhu, Wayne Wu, Chen Qian, Qiang Zhou, Bolei Zhou, Chen Change Loy
We present a lightweight video motion retargeting approach TransMoMo that is capable of transferring motion of a person in a source video realistically to another video of a target person.
1 code implementation • 4 Oct 2019 • Wentao Zhu, Andriy Myronenko, Ziyue Xu, Wenqi Li, Holger Roth, Yufang Huang, Fausto Milletari, Daguang Xu
Furthermore, we design three segmentation frameworks based on the proposed registration framework: 1) atlas-based segmentation, 2) joint learning of both segmentation and registration tasks, and 3) multi-task learning with atlas-based segmentation as an intermediate feature.
no code implementations • 2 Oct 2019 • Holger Roth, Wentao Zhu, Dong Yang, Ziyue Xu, Daguang Xu
In the first step, we register a small set of five LGE cardiac magnetic resonance (CMR) images with ground truth labels to a set of 40 target LGE CMR images without annotation.
no code implementations • 2 Oct 2019 • Wenqi Li, Fausto Milletarì, Daguang Xu, Nicola Rieke, Jonny Hancox, Wentao Zhu, Maximilian Baust, Yan Cheng, Sébastien Ourselin, M. Jorge Cardoso, Andrew Feng
Due to medical data privacy regulations, it is often infeasible to collect and share patient data in a centralised data lake.
no code implementations • 18 Jun 2019 • Wentao Zhu, Yufang Huang, Mani A. Vannan, Shizhen Liu, Daguang Xu, Wei Fan, Zhen Qian, Xiaohui Xie
In this work, we propose a neural multi-scale self-supervised registration (NMSR) method for automated myocardial and cardiac blood flow dense tracking.
no code implementations • 12 Mar 2019 • Wentao Zhu
Second, we will demonstrate how to use the weakly labeled data for the mammogram breast cancer diagnosis by efficiently design deep learning for multi-instance learning.
2 code implementations • 15 Aug 2018 • Wentao Zhu, Yufang Huang, Liang Zeng, Xuming Chen, Yong liu, Zhen Qian, Nan Du, Wei Fan, Xiaohui Xie
Methods: Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot.
2 code implementations • 14 May 2018 • Wentao Zhu, Yeeleng S. Vang, Yufang Huang, Xiaohui Xie
Recently deep learning has been witnessing widespread adoption in various medical image applications.
1 code implementation • 25 Jan 2018 • Wentao Zhu, Chaochun Liu, Wei Fan, Xiaohui Xie
DeepLung consists of two components, nodule detection (identifying the locations of candidate nodules) and classification (classifying candidate nodules into benign or malignant).
Ranked #4 on
Lung Nodule Classification
on LIDC-IDRI
1 code implementation • 24 Oct 2017 • Wentao Zhu, Xiang Xiang, Trac. D. Tran, Gregory D. Hager, Xiaohui Xie
Mass segmentation provides effective morphological features which are important for mass diagnosis.
no code implementations • 16 Sep 2017 • Wentao Zhu, Chaochun Liu, Wei Fan, Xiaohui Xie
Considering the 3D nature of lung CT data, two 3D networks are designed for the nodule detection and classification respectively.
Automated Pulmonary Nodule Detection And Classification
Classification
+1
1 code implementation • 23 May 2017 • Wentao Zhu, Qi Lou, Yeeleng Scott Vang, Xiaohui Xie
Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning (MIL) for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned ROIs.
no code implementations • 12 Mar 2017 • Qing Han, Wentao Zhu, Yang Shi
Today, detection of anomalous events in civil infrastructures (e. g. water pipe breaks and leaks) is time consuming and often takes hours or days.
1 code implementation • 18 Dec 2016 • Wentao Zhu, Xiang Xiang, Trac. D. Tran, Xiaohui Xie
Experimental results on two public datasets, INbreast and DDSM-BCRP, show that our end-to-end network combined with adversarial training achieves the-state-of-the-art results.
no code implementations • 18 Dec 2016 • Wentao Zhu, Qi Lou, Yeeleng Scott Vang, Xiaohui Xie
Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned costly need to annotate the training data.
no code implementations • 24 Mar 2016 • Wentao Zhu, Cuiling Lan, Junliang Xing, Wen-Jun Zeng, Yanghao Li, Li Shen, Xiaohui Xie
Skeleton based action recognition distinguishes human actions using the trajectories of skeleton joints, which provide a very good representation for describing actions.
no code implementations • 27 Sep 2015 • Wentao Zhu, Jun Miao, Laiyun Qing, Xilin Chen
Compared to traditional deep learning methods, the implemented feature learning method has much less parameters and is validated in several typical experiments, such as digit recognition on MNIST and MNIST variations, object recognition on Caltech 101 dataset and face verification on LFW dataset.
1 code implementation • 25 Jan 2015 • Wentao Zhu, Jun Miao, Laiyun Qing
Extreme learning machine (ELM) is an extremely fast learning method and has a powerful performance for pattern recognition tasks proven by enormous researches and engineers.