Search Results for author: Qingyu Li

Found 7 papers, 1 papers with code

GlobalBuildingMap -- Unveiling the Mystery of Global Buildings

no code implementations22 Apr 2024 Xiao Xiang Zhu, Qingyu Li, Yilei Shi, Yuanyuan Wang, Adam Stewart, Jonathan Prexl

A joint analysis of building maps and solar potentials indicates that rooftop solar energy can supply the global energy consumption need at a reasonable cost.

AIO2: Online Correction of Object Labels for Deep Learning with Incomplete Annotation in Remote Sensing Image Segmentation

1 code implementation3 Mar 2024 Chenying Liu, Conrad M Albrecht, Yi Wang, Qingyu Li, Xiao Xiang Zhu

AIO2 utilizes a mean teacher model to enhance training robustness with noisy labels to both stabilize the training accuracy curve for fitting in ACT and provide pseudo labels for correction in O2C.

Earth Observation Image Segmentation +1

Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training

no code implementations17 May 2022 Qingyu Li, Yilei Shi, Xiao Xiang Zhu

Considering that rich information is also encoded in feature maps, we propose to integrate the consistency of both features and outputs in the end-to-end network training of unlabeled samples, enabling to impose additional constraints.

Semi-Supervised Semantic Segmentation

Instance segmentation of buildings using keypoints

no code implementations6 Jun 2020 Qingyu Li, Lichao Mou, Yuansheng Hua, Yao Sun, Pu Jin, Yilei Shi, Xiao Xiang Zhu

The detected keypoints are subsequently reformulated as a closed polygon, which is the semantic boundary of the building.

Instance Segmentation Segmentation +1

Building Footprint Generation by IntegratingConvolution Neural Network with Feature PairwiseConditional Random Field (FPCRF)

no code implementations11 Feb 2020 Qingyu Li, Yilei Shi, Xin Huang, Xiao Xiang Zhu

Due to the complexity of buildings, the accurate and reliable generation of the building footprint from remote sensing imagery is still a challenging task.


Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding

no code implementations8 Nov 2019 Yilei Shi, Qingyu Li, Xiao Xiang Zhu

Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks.

General Classification Segmentation +1

Building Footprint Generation Using Improved Generative Adversarial Networks

no code implementations26 Oct 2018 Yilei Shi, Qingyu Li, Xiao Xiang Zhu

The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes.

Cannot find the paper you are looking for? You can Submit a new open access paper.