Ziyang Wang

I am a researcher at The Alan Turing Institute. Prior to this, I completed my DPhil (PhD) degree in Computer Science at the University of Oxford in 2024, MRes (Master of Research) degree with distinction at Imperial College London in 2018, and BEng (Bachelor of Engineering) degree at Xi’an Jiaotong University in 2017.

Feel free to reach out if you'd like to collaborate, share ideas, or simply connect.

Email: ziyang.wang17 [at] gmail.com OR zwang [at] turing.ac.uk

Research Interests

Artificial Intelligence, Deep Learning, Computer Vision, Data-Centric Engineering, Healthcare AI.

Network Architecture: Convolutional Neural Network, Vision Transformer, State Space Model.
Network Training: Supervised Learning, Weakly-Supervised Learning, Self-Supervised Learning, Semi-Supervised Learning, Mixed-Supervised Learning, Noise-Robust Learning, Interactive Machine Learning.
Computer Vision for Healthcare: Medical Image Segmentation, Medical Image Registration, Depth Estimation, Human Gait Analysis, Surgical Robot Vision.

GitHub Projects

I only list GitHub projects for which I am the owner & initial contributor. Find more information here -> [Link]

Mamba-UNet [Code] Github stars
Supervised Medical Image Segmentation [Code] Github stars
UNet Zoo [Code] Github stars
Semi-Supervised Medical Image Segmentation [Code] Github stars
Weakly-Supervised Medical Image Segmentation [Code] Github stars
Weakly-Supervised Surgical Robot Segmentation [Code] Github stars
Healthcare Robot [Code] Github stars
Step Motor Driver [Code] Github stars
Awesome Medical Image Segmentation Dataset [Code] Github stars
MixSegNet [Code] Github stars
TriConvUNeXt [Code] Github stars
CVPixUNet [Code] Github stars
VMambaMorph [Code] Github stars
Awesome VMamba [Code] Github stars
Weak-Mamba-UNet [Code] Github stars

Academic Service

Find more information here -> [Link]

Journal Reviewer:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Medical Imaging (TMI)
IEEE Transactions on Geoscience and Remote Sensing (TGRS)
Elsevier - Pattern Recognition
Elsevier - Knowledge-Based Systems
Elsevier - Engineering Applications of Artificial Intelligence
Elsevier - Artificial Intelligence in Medicine
Elsevier - Computers in Biology and Medicine
Elsevier - Neurocomputing
Elsevier - Biomedical Signal Processing and Control
Elsevier - Image and Vision Computing
Elsevier - Computer Methods and Programs in Biomedicine
Springer - International Journal of Multimedia Information Retrieval
Springer - Journal of Imaging Informatics in Medicine
Springer - Cognitive Computation
Springer - Cluster Computing
Springer - Journal of Real-Time Image Processing
Nature - Scientific Reports
Wiley - Medical Physics

Conference Reviewer:
ICLR, ICRA, IROS, ICASSP, ICIP, IJCNN, ICPR, MICCAI-W, ICCV-W

Selected Publications

I only list some of papers for which I am the First/Corresponding Author since 2021. Find more information here -> [Link]

  • “Rethinking Hybrid Convolution- & Vision Transformer-based U-Shape Network with Pixel-Level Feature Learning for Retinal Vessel Segmentation.” Engineering Applications of Artificial Intelligence, 2024. [Code] [Under Review]
  • “S4RoboFormer: Scribble-Supervised Segmentation for Surgical Robots via Augmented Consistency Training.” ICASSP, 2024. [Code] [Under Review]
  • “OC4-ReID: Occluded Cloth-Changing Person Re-Identification.” ICASSP, 2024. [Code] [Under Review]
  • “Spectral Enhancement and Pseudo-Anchor Guidance for Infrared-Visible Person Re-identification.” ICASSP, 2024. [Code] [Under Review]
  • “Quadruple-Consistency Vision Transformer for Medical Image Segmentation with Limited Number of Sparse Annotations.” ICIP, 2024. [Code] [In Press]
  • “Semi-Mamba-UNet: Pixel-Level Contrastive Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation.” Knowledge-Based Systems, 2024. [Paper], [GitHub 410+ Stars], [Code]
  • “GaitFormer: Leveraging Dual-Stream Spatial-Temporal Vision Transformer via a Single Low-Cost RGB Camera for Clinical Gait Analysis.” Knowledge-Based Systems, 2024. [Paper]
  • “TriConvUNeXt: A Pure CNN-based Lightweight Symmetrical Network for Biomedical Image Segmentation.” Journal of Imaging Informatics in Medicine, 2024. [Paper], [Code]
  • “VMambaMorph:a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Module.” Arxiv, 2024. [Paper], [Code]
  • “Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation.” Arxiv, 2024. [Paper], [Code]
  • “Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation.” Arxiv, 2024. [GitHub 410+ Stars], [Paper], [Code]
  • “MixSegNet: Fusing Multiple Supervisory Signals with Multiple Views of Networks for Medical Image Segmentation.” Engineering Applications of Artificial Intellligence, 2024. [Paper], [Code]
  • “Dual-Contrastive Dual-Consistency Dual-Transformer: A Semi-Supervised Approach to Medical Image Segmentation.” ICCV. 2023. [Paper], [Code]
  • “Dealing with Unreliable Annotations: A Noise-Robust Network for Semantic Segmentation through A Transformer-Improved Encoder and Convolution Decoder.” Applied Sciences, 2023. [100% APC Discount], [Paper], [Code]
  • “Weakly Supervised Medical Image Segmentation Through Dense Combinations of Dense Pseudo-Labels.” MICCAI DEMI, 2023. [Best Paper Award], [Paper], [Code]
  • “Exigent Examiner and Mean Teacher: A Novel 3D CNN-based Semi-Supervised Learning Framework for Brain Tumor Segmentation.” MICCAI MILLanD, 2023. [Paper], [Code]
  • “Computationally-efficient vision transformer for medical image semantic segmentation via dual pseudo-label supervision.” ICIP. 2023. [IEEE Travel Grant], [Paper], [Code]
  • “When CNN meet with ViT: Towards semi-supervised learning for multi-class medical image semantic segmentation.” ECCV, 2022. [Paper], [Code]
  • “Adversarial Vision Transformer for Medical Image Semantic Segmentation with Limited Annotations.” BMVC, 2022. [Paper], [Supp], [Code]
  • “Triple-view feature learning for medical image segmentation.” MICCAI REMIA, 2022. [Paper], [Code]
  • “An uncertainty-aware transformer for MRI cardiac semantic segmentation via mean teachers.” MIUA, 2022. [Paper], [Code]
  • “RAR-U-Net: a residual encoder to attention decoder by residual connections framework for spine segmentation under noisy labels.” ICIP, 2021. [Paper], [Code]
  • “Quadruple augmented pyramid network for multi-class COVID-19 segmentation via CT.” EMBC, 2021. [Paper]
  • “A Single RGB Camera based Gait Analysis with a Mobile Tele-Robot for Healthcare.” EMBC, 2021. [Paper], [Code]

Support Me

Ethereum:
0xfF187c04E6a9c722FC116660764AB828eCE55917
0x63909d630eabc84c3Ad1519264783f7f9Cf2146b

Bitcoin:
33JgYq6qizqcAVPruKtD1tEYKfsEVJebpf