xingcw Goto Github PK

agile_flight

Developing and Comparing Vision-based Algorithms for Vision-based Agile Flight

docker-nomachine

running nomachine in docker to render images from headless server

dpt

Dense Prediction Transformers

eth-cs-notes

Lecture notes and cheatsheets for Master's in Computer Science at ETH Zurich

flightmare

An Open Flexible Quadrotor Simulator

flightmare_unity

Unity for flightmare

gitignore

A collection of useful .gitignore templates

gosmatch-python

Reimplementation and correction of GOSMatch based on its official codes

iacv_lab

ETH Image Analysis and Computer Vision

iml_2021spring

mask2former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

mpc2021_pe

multimae

MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022

pdm4ar_project

probing-vits

Probing the representations of Vision Transformers.

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

ros_2021

Programming for Robotics - ROS ETH

semantic_graph

Implementation of IROS20 paper - "Semantic Graph Based Place Recognition for 3D Point Clouds"

transformer-explainability

Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

transformer-mm-explainability

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vis_attention

A test repo to visualize the attention maps of the SotA models using explainable visualization methods

vision_backbones

A repo to test SotA backbones for the vision representation learning in RL for the thesis project. It's NDA-free, totally public, without any crediential codes from my host lab.

vit-explain

Explainability for Vision Transformers

xingcw.github.io

My personal website - built with React, React-Router, React-Snap for Static-Export, and GitHub Pages.