dianch Goto Github PK

adacontrast

Official repository of CVPR '22 paper "Contrastive Test-Time Adaptation"

awesome-visual-transformer

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

clip

Contrastive Language-Image Pretraining

computer_vision_basics

Implementation of some computer vision basics

deep_reinforcement_learning

Implementation of discrete Q-Learning, and DQN, REINFORCE (discrete and continuous) with experiments on OpenAI gym models

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

gmm_color_segmentation

Color segmentation using Gaussian Mixture Models

hmm_gesture_recognition

Hidden Markov Models are trained and applied on IMU readings to recognize hand gestures.

hw01-noisy-terrain

indoor_slam_for_mobile_robots

Implementation of LIDAR-based SLAM on 2-D grid map using particle filtering

interactive_computer_graphics

Step by step projects experimenting with OpenGL under Qt 5 framework, culminating in a Mini-Minecraft interactive game.

mask-rcnn

This is a Pytorch implementation of Mask-RCNN from scratch, such that architecture and training & eval procedures are explicit. No magic registering or templates as in higher level wrapper frameworks.

monodepth2

Pytorch re-implementation of paper Digging Into Self-Supervised Monocular Depth Estimation

numpy-deep-learning

A deep learning framework written from scratch using NumPy.

omnidata

A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]

petr

PETR: Position Embedding Transformation for Multi-View 3D Object Detection

quaternion_based_ukf

Quaternion-based UKF to robustly estimate the pose, with panorama stitching to visualize the estimation

repdistiller

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

shan_shui_inf

Procedurally understandably generated Chinese landscape painting.

shot

code released for our ICML 2020 paper "Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation"

simmim

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".