by-liu
Applied Scientist @ Amazon AWS AI. Research Interests : machine learning, deep learning, computer vision, medical image analysis.
Amazon AWS AIVancouver, Canada
Pinned Repositories
academic-kickstart
📝 Easily create a beautiful website using Academic, Hugo, and Netlify
albumentations-demo
The service for the demonstration of transforms in Albumentations library
by-liu.github.io
calibration-framework
Python Framework to calibrate confidence estimates of classifiers like Neural Networks
CALS
Code for our method CALS (Class Adaptive Label Smoothing) for network calibration. To Appear at CVPR 2023. Paper: https://arxiv.org/abs/2211.15088
ConfKD
Code for our paper : Mixed-supervised segmentation: Confidence maximization helps knowledge distillation. https://arxiv.org/abs/2109.10902
donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
lightning-hydra-template
Deep Learning project template best practices with Pytorch Lightning, Hydra, Tensorboard.
MbLS
Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/2111.15430
SegLossBias
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
by-liu's Repositories
by-liu/MbLS
Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/2111.15430
by-liu/SegLossBias
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
by-liu/CALS
Code for our method CALS (Class Adaptive Label Smoothing) for network calibration. To Appear at CVPR 2023. Paper: https://arxiv.org/abs/2211.15088
by-liu/ConfKD
Code for our paper : Mixed-supervised segmentation: Confidence maximization helps knowledge distillation. https://arxiv.org/abs/2109.10902
by-liu/academic-kickstart
📝 Easily create a beautiful website using Academic, Hugo, and Netlify
by-liu/albumentations-demo
The service for the demonstration of transforms in Albumentations library
by-liu/by-liu.github.io
by-liu/calibration-framework
Python Framework to calibrate confidence estimates of classifiers like Neural Networks
by-liu/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
by-liu/lightning-hydra-template
Deep Learning project template best practices with Pytorch Lightning, Hydra, Tensorboard.
by-liu/maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
by-liu/MI-based-Regularized-Semi-supervised-Segmentation
This is a place holder for an incomming paper.
by-liu/mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
by-liu/moco
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
by-liu/MSL-student-becomes-master
by-liu/myutil
some personal scripts and config
by-liu/nnUNet
by-liu/OpenUnReID
Open-source toolbox for unsupervised or domain adaptive object re-ID.
by-liu/personal_website
by-liu/Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
by-liu/RetinalApp
by-liu/SegLoss
A collection of loss functions for medical image segmentation
by-liu/segmentation_viewer
A really simple tool to visualize different segmentation results
by-liu/SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
by-liu/Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
by-liu/TA3N
[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)
by-liu/ttda