I am a Ph.D student at AIM Group in EE department, The Chinese University of Hong Kong, supervised by Dr. Yixuan Yuan. I focus on Deep learning, Computer vision, and Medical image analysis. Before that, I received my M.Sc. degree with the Department of Control Science and Engineering, Harbin Institute of Technology and B.Sc. Degree at Honors School, Harbin Institute of Technology, where I was supervised by Prof. Xiaoguang Di.
Email  /  Google Scholar  /  Github
I'm interested in building efficient vision models with unsupervised domain adaptation, pruning for classification/detection/segmentation/super resolution tasks.
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention Xinyu Liu, Houwen Peng, Ningxin Zheng, Yuqing Yang, Han Hu, Yixuan Yuan. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2023), 2023 |
|
Intervention & Interaction Federated Abnormality Detection with Noisy Clients Xinyu Liu, Wuyang Li, Yixuan Yuan. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022 Oral), 2022 |
|
Semi-supervised Medical Image Classification with Temporal Knowledge-Aware Regularization Qiushi Yang, Xinyu Liu, Zhen Chen, Bulat Ibragimov, Yixuan Yuan. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022), 2022 |
|
Towards Robust Adaptive Object Detection under Noisy Annotations Xinyu Liu, Wuyang Li, Qiushi Yang, Baopu Li, Yixuan Yuan. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022 |
|
SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection Wuyang Li, Xinyu Liu, Yixuan Yuan. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022 Oral, Best paper final list), 2022 |
|
SCAN: Cross Domain Object Detection with Semantic Conditioned Adaptation Wuyang Li, Xinyu Liu, Xiwen Yao, Yixuan Yuan. The AAAI Conference on Artificial Intelligence (AAAI 2022 Oral), 2022 |
|
Exploring Gradient Flow Based Saliency for DNN Model Compression Xinyu Liu, Baopu Li, Zhen Chen, Yixuan Yuan. |
|
Joint Polyp Detection and Segmentation with Heterogeneous Endoscopic Data Wuyang Li, Chen Yang, Jie Liu, Xinyu Liu, Xiaoqing Guo, Yixuan Yuan. IEEE International Symposium on Biomedical Imaging Endoscopy Workshop (EndoCV 2021), 2021 |
Generalized Gradient Flow Based Saliency for Pruning Deep Convolutional Neural Networks Xinyu Liu, Baopu Li, Zhen Chen, Yixuan Yuan. International Journal of Computer Vision (IJCV), 2023 |
|
Decoupled Unbiased Teacher for Source-Free Domain Adaptive Medical Object Detection Xinyu Liu, Wuyang Li, Yixuan Yuan. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 |
|
SIGMA++: Improved Semantic-complete Graph Matching for Domain Adaptive Object Detection Wuyang Li, Xinyu Liu, Yixuan Yuan. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 |
|
SCAN++: Enhanced Semantic Conditioned Adaptation for Domain Adaptive Object Detection Wuyang Li, Xinyu Liu, Yixuan Yuan. |
|
A Source-free Domain Adaptive Polyp Detection Framework with Style Diversification Flow Xinyu Liu, Yixuan Yuan. IEEE Transactions on Medical Imaging (TMI), 2022 |
|
Consolidated domain adaptive detection and localization framework for cross-device colonoscopic images Xinyu Liu, Xiaoqing Guo, Yajie Liu, Yixuan Yuan. |
|
TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks Xinyu Liu, Xiaoguang Di. IET Computer Vision (IET-CVI), 2021 |
|
Global Context Parallel Attention for Anchor-free Instance Segmentation in Remote Sensing Images Xinyu Liu, Xiaoguang Di. IEEE Geoscience and Remote Sensing Letters (GRSL), 2020 |
|
Vector Encoded Bounding Box Regression for Detecting Remote Sensing Objects with Anchor-free Methods Xinyu Liu, Xiaoguang Di, Junde Wu, Jiehao Huang. International Journal of Remote Sensing (IJRS), 2020 |
Microsoft Research Asia
Research Intern, May. 2022 - Sept. 2022 |
|
Deepwise
Research Intern, May. 2019 - Jul. 2019 |