Name: Bingyuan Liu
Type: User
Company: Amazon AWS AI
Bio: Applied Scientist @ Amazon AWS AI.
Research Interests : machine learning, deep learning, computer vision, medical image analysis.
Twitter: bing_bingyuan
Location: Vancouver, Canada
Blog: https://by-liu.github.io
Bingyuan Liu's Projects
📝 Easily create a beautiful website using Academic, Hugo, and Netlify
The service for the demonstration of transforms in Albumentations library
Python Framework to calibrate confidence estimates of classifiers like Neural Networks
Code for our method CALS (Class Adaptive Label Smoothing) for network calibration. To Appear at CVPR 2023. Paper: https://arxiv.org/abs/2211.15088
Code for our paper : Mixed-supervised segmentation: Confidence maximization helps knowledge distillation. https://arxiv.org/abs/2109.10902
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Deep Learning project template best practices with Pytorch Lightning, Hydra, Tensorboard.
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/2111.15430
This is a place holder for an incomming paper.
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
some personal scripts and config
Open-source toolbox for unsupervised or domain adaptive object re-ID.
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
A collection of loss functions for medical image segmentation
Code for the paper : Do we really need dice? The hidden region-size biases of segmentation losses. MeDIA 2023. https://www.sciencedirect.com/science/article/abs/pii/S136184152300275X
A really simple tool to visualize different segmentation results
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)