Zaiwang Gu
2022-08 ~ now,
|
|
Recent News and Awards:
- [11/2024] One paper accepted by TMLR: "When low-vision task meets dense prediction tasks with less data: an auxiliary self-trained geometry regularization".
- [09/2024] Happy to be named among as
"Top 2% Most Cited Scientists for 2023" by Stanford University.[Link] - [09/2024] One paper accepted by MICCAI 2024: "Coarse-Grained Mask Regularization for Microvascular Obstruction Identification from Non-contrast Cardiac Magnetic Resonance".
- [07/2024] One paper accepted by CVPR 2024: "Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching".
- [02/2024] One paper accepted by AAAI 2024: "SuperJunction: Learning-Based Junction Detection for Retinal Image Registration".
- [08/2022] IEEE TMI "Distinguished Reviewer" Gold Level
- [12/2020] The "Outstanding Contribution Award" in Ubtech Research!
- [07/2020] The CE-Net becomes
"ESI Highly Cited Paper", "ESI Hot Paper" . - [07/2019] MICS 2019
"Best Poster Award" - [07/2018] ICCCV 2018
"Best Presentation Award"
Research Interests:
-
3D Vision:
- Depth estimation and completion
- Object detection
-
Medical Image Analysis:
- "2D Medical Image Segmentation"
Projects:
This project aims to provide the efficient and effective depth estimation and completion, stereo matching approaches.
My responsibility for this project is to apply the object detection and recognition algorithms to the company’s various types of robots, such as low-power robot toys for the customers and high-power industrial robots. To be specific, we first adopt some advanced AI algorithms to locate and recognize hundreds of objects. Then, we focus on the corner cases, where the existing AI algorithms fail on our actual scenes. Finally, based on the deficiency of current methods, we modify and propose a new algorithm to enhance object recognition. Now, our intelligent algorithm could recognize up to 300 categories of objects
This project aims to improve the diagnosis performances of fundus diseases, including Diabetic Retinopathy, Glaucoma, and Age-related macular degeneration. An effective and efficient medical image segmentation algorithm is the key to the accurate diagnosis of different diseases. Based on the rapid development of AI algorithms, we proposed a general 2D medical image segmentation framework, context encoder network (termed as CE-Net). We evaluate the proposed CE-Net on five individual medical segmentation tasks with multi modalities and multi organs. The comparisons experiments show that the proposed CE-Net outperforms the other advanced AI segmentation methods. We published this work in the journal, IEEE transactions on Medical Imaging(TMI). This paper has achieved up to 1900 citations on the google scholar website and becomes an ESI-Highly-Cited paper.
Activities:
- Journal Reviewer:
- IEEE Transactions on Medical Imaging (TMI).
- IEEE Transactions on Biomedical Engineering (TBME) .
- IEEE Transactions on Neural Networks and Learning Systems (TNNLS) .
- IEEE Journal of Biomedical and Health Informatics (JBHI) .
- Conference Reviewer:
- MICCAI (2022, 2021, 2020, 2019)
- OMIA (2022, 2021, 2020, 2019)
- ICLR (2023)
Selected Publications:
[Google Scholar Profile] for full publication list.
2021:
- Yepeng Liu, Zaiwang Gu, Shenghua Gao, Dong Wang, Yusheng Zeng, Jun Cheng and Shenghua Gao, "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation", BMVC 2021, [arXiv]
2020:
- Kang Zhou, Yuting Xiao, Jianlong Yang, Jun Cheng, Wen liu, Weixin Luo, Zaiwang Gu, Jiang Liu and Shenghua Gao, "Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images ", ECCV 2020, [arXiv]
2019:
- Zaiwang Gu, Jun Cheng, Huazhu F, Kang Zhou, Huaying Hao, Yitian Zhao, Tianyang Zhang, Shenghua Gao, and Jiang Liu, "CE-Net: Context Encoder Network for 2D Medical Image Segmentation", IEEE TMI, 2019. [arXiv] [Code] "ESI Highly Cited Paper"
- Tianyang Zhang, Jun Cheng, Huazhu Fu, Zaiwang Gu, Yitian Xiao, Kang Zhou, Shenghua Gao, Rui Zheng, Jiang Liu "Noise adaptation generative adversarial network for medical image analysis", IEEE TMI, 2019. [Paper]
- Lei Mou, Li Chen, Jun Cheng, Zaiwang Gu, Yitian Zhao, Jiang Liu, "Dense Dilated Network with Probability Regularized Walk for Vessel Detection", IEEE TMI, 2019. [Paper]
- Yuming Jiang, Lixin Duan, Jun Cheng, Zaiwang Gu, Hu Xia, Huazhu Fu, Changsheng Li, Jiang Liu "JointRCNN: A Region-based Convolutional Neural Network for Optic Disc and Cup Segmentation", in IEEE TBME, 2019. [Paper]
- Lei Mou, Yitian Zhao, Li Chen, Jun Cheng, Zaiwang Gu, Huaying Hao, Hong Qi, Yalin Zheng, Alejandro Frangi, Jiang Liu, "CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation", in MICCAI, 2019. [Paper]
- Tianyang Zhang, Huazhu Fu, Yitian Zhao, Jun Cheng, Mengjie Guo, Zaiwang Gu, Bing Yang, Yuting Xiao, Shenghua Gao, Jiang Liu "SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis", in MICCAI, 2019. [Paper]
2018:
- Jun Cheng, Zhengguo Li, Zaiwang Gu, Huazhu Fu, DWK Wong, Jiang Liu, "Structure-preserving guided retinal image filtering for optic disc analysis", IEEE TMI, 2018. [Paper]