charzharr Goto Github PK

3d-medseg-pretraining

Project on discovering new effective pretraining methods for 3D medical image segmentation.

advanced-algorithms-project

awesome-semi-supervised-learning

:scroll: An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

bibm-ssl

charzharr.github.io

My personal website for contact information, publications, projects, works, and interests.

cv-final-evaluation

deep-learning-drizzle

Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!

deep-medical-toolkit

A personal code toolkit for the purpose of facilitating medical imaging research. The main components of this library consists of a neural network model zoo, image transformations (for preprocessing & augmentation), common metrics/losses, fast multiprocessed data loading, and data structures for image samples.

hierarchical-contrastive-pretraining

Project on improving the instance discrimination task in contrastive pretraining by leveraging feature-based hierarchical clustering.

latex-201

learning-deep-learning

My notes, experiences, progress, and resources for building Deep Learning expertise.

medicaldetectiontoolkit

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

miccai23-swipe-implicit-segmentation

SwIPE (Segmentation with Implicit Patch Embeddings) is a medical image segmentation approach that utilizes implicit neural representations (INRs) to learn continuous representations rather than discrete representations commonly seen in modern methods (e.g., CNNs, transformers, or combinations of both).

mml-book

Code / solutions for Mathematics for Machine Learning (MML Book)

rere

Library for common functions, tasks, and utilities for vision research (rere = research resources).

s3-computer-vision-project

segmentation-label-reduction

sota-medseg

SOTA medical image segmentation methods based on various challenges

unet3plus_pth

UNet3+/ UNet++/UNet, used in Deep Automatic Portrait Matting in Pytorth