Yingbin Bai

About me

I am Yingbin Bai, a PhD student at the University of Sydney. My supervisor is Prof. Tongliang Liu. Prior to joining the University of Sydney, I gained several years of industry experience, where I focused on utilizing IT techniques to solve agriculture problems. I strongly believe that machine learning will play a crucial role in addressing agricultural issues. During my free time, I enjoy traveling and photography.

My research interests encompass weakly supervised learning and unsupervised representation learning. If you have any ideas or encounter any problems related to these areas, I would be more than happy to discuss and collaborate.

  • Address: Sydney, Australia
  • Email:  ybai6430@uni.sydney.edu.au


Publications

Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping
      Yingbin Bai, Zhongyi Han, Erkun Yang, Jun Yu, Bo Han, Dadong Wang, Tongliang Liu
      NeurIPS 2023

RSA: Reducing Semantic Shift from Aggressive Augmentations for Self-supervised Learning
      Yingbin Bai, Erkun Yang, Zhaoqing Wang, Yuxuan Du, Bo Han, Cheng Deng, Dadong Wang, Tongliang Liu
      NeurIPS 2022

Understanding and Improving Early Stopping for Learning with Noisy Labels
      Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, and Tongliang Liu
      NeurIPS 2021

Me-Momentum: Extracting Hard Confident Examples from Noisily Labeled Data
      Yingbin Bai and Tongliang Liu
      ICCV 2021
      Oral


Academic Activity

09/2021, I partcipated in MICCAI QUBIQ Challenge 2021, and got the 2nd place.