MADONOKOUKI

gcce2022_instancewise_center_loss

psivt23_scramblemix

SPG_EI2020

Code of experiments in "Scrambling Parameter Generation to Improve Perceptual Information Hiding" paper (EI 2020)

cv-snippets

My code snippets for computer vision.

dda

Differentiable Data Augmentation Library

diffvg

Differentiable Vector Graphics Rasterization

ICCV2019-LearningToPaint

ICCV2019 - A painting AI that can reproduce paintings stroke by stroke using deep reinforcement learning.

InstaHide

InstaHide: Instance-hiding Schemes for Private Distributed Learning

lambda-networks

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

LIVE-Layerwise-Image-Vectorization

[CVPR 2022 Oral] Towards Layer-wise Image Vectorization

MADONOKOUKI.github.io

Medium-Tutorials

mini-imagenet-tools

Tools for generating mini-ImageNet dataset and processing batches

ned_ros

Ned ros stack

neural_real_estate

niryo_one_ros

Niryo One ROS stack

Open3D

Open3D: A Modern Library for 3D Data Processing

opencv

Open Source Computer Vision Library

pix2pixHD

Synthesizing and manipulating 2048x1024 images with conditional GANs

privacy

Library for training machine learning models with privacy for training data

pytorch-classification

Classification with PyTorch.

Random-Shadows-Highlights

A new data augmentation method for extreme lighting conditions.

RepDistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

rigid_transform_3D

segraph

The segraph library creates graphs from SLIC superpixels. It can be used for using CRF for image segmentation https://pypi.python.org/pypi/segraph/0.5

SIA-GAN

stylized-neural-painting

Official Pytorch implementation of the preprint paper "Stylized Neural Painting", in CVPR 2021.

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

vision

Datasets, Transforms and Models specific to Computer Vision

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch