Displaying present location in the site.

Machine Learning

Our Machine Learning Team is mainly devoted to:

  1. Developing autoML technology under scenarios such as low data and weak tags to improve the operational efficiency and interpretability of AI and develop a reliable AI system;
  2. Conducting research on uncertainty probabilistic inference technology and combining with various deep learning models to develop a highly reliable medical diagnosis AI system.

As a young research team, we not only published our research results at important academic conferences such as MICCAI, IJCNN, ICIP, etc., but also cooperated with many well-known domestic hospitals in the field of AI for medical diagnosis and quickly applied research results to clinical practice.

Publication

  • 【ISBI 2021】UNCERTAINTY-GUIDED ROBUST TRAINING FOR MEDICAL IMAGE SEGMENTATION
  • 【IJCNN 2021 (Accepted)】Model Performance Inspection of Deep Neural Networks by Decomposing Bayesian Uncertainty Estimates
  • 【IJCNN 2021 (Accepted)】Layerwise Approximate Inference for Bayesian Uncertainty Estimates on Deep Neural Networks
  • 【MICCAI 2020】An Effective Data Refinement Approach for Upper Gastrointestinal Anatomy Recognition
  • 【ICIP 2020】Loss Rescaling by Uncertainty Inference for Single-stage Object Detection
  • 【IJCNN 2020】A Layer-wise Adversarial Training Approach to Improve Adversarial Robustness