Qingyun's Projects
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).
Awesome Remote Sensing Toolkit based on PaddlePaddle.
pytorch implementation of the paper, points as queries: weakly semi-supervised object detection by points
Personal website
Semantic segmentation on remote sensing data sets with the mmsegmentation of OpenMMLab 2.0. Personal maintenance and use.
[TGRS 2024] Official implementation of "Co-training Transformer for Remote Sensing Image Classification, Segmentation and Detection".
SAM (Segment Anything Model) for generating rotated bounding boxes with MMRotate, which is a comparison method of H2RBox-v2.
[GRSL 2022] Official implementation of "Two-Branch Pure Transformer for Hyperspectral Image Classification".
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
A playbook for systematically maximizing the performance of deep learning models.
Implement object tracking task of SAR Video. This repo is built on mmtracking (OpenMMLab 1.0 series).
Forked from the official repo for the paper "An Empirical Study of Remote Sensing Pretraining"