hankyul's Projects
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
annotated image model paper series
pip install antialiased-cnns to improve stability and accuracy
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
Reference implementation for Blueprint Separable Convolutions (CVPR 2020)
λ²μ€ μΈμ μ
CapsuleNet implementation
my pytorch package
diffusion-tutorial-notebook
Domain Adaptation
EfficientNetV2 pytorch (pytorch lightning) implementation with pretrained model
This is an attempt to use transformers and self attention in order to convert English descriptions into Python code.
Face Recognition
faster rcnn implementation in pytorch(pytorch-lightning)
ajou 2021 spring advanced computer architecture project
Graph Neural Network
hahahaha
Official implementation of the paper "Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification, ICCV2021"
Image Classification
1000 images, one per image-net class. For easy visualization/exploration of classes.
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper
State-of-the-art 2D and 3D Face Analysis Project
Knowledge Distilation
Collection of Pytorch lightning tutorial form as rich scripts automatically transformed to ipython notebooks.
Convert face dataset to masked dataset
[ECCV 2022] unofficial pytorch implementation of the paper "MaxViT: Multi-Axis Vision Transformer"
machine learning study
MMCAP pytorch implementation