Browsing NR vitenarkiv by Author "Liu, Qinghui"

Now showing items 1-6 of 6

    • COASTAL HABITAT MAPPING WITH UAV MULTI-SENSOR DATA: AN EXPERIMENT AMONG DCNN-BASED APPROACHES 

      Liu, Yi; Liu, Qinghui; Sample, James Edward; Hancke, Kasper; Salberg, Arnt Børre (Journal article; Peer reviewed, 2022)
      With recent abundant availability of high resolution multi-sensor UAV data and rapid development of deep learning models, efficient automatic mapping using deep neural network is becoming a common approach. However, with ...

    • Dense dilated convolutions merging network for land cover classification 

      Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt Børre (Journal article; Peer reviewed, 2020)
      Land cover classification of remote sensing images is a challenging task due to limited amounts of annotated data, highly imbalanced classes, frequent incorrect pixel-level annotations, and an inherent complexity in the ...

    • Multi-View Self-Constructing Graph Convolutional Networks With Adaptive Class Weighting Loss for Semantic Segmentation 

      Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt Børre (Chapter, 2020)
      We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes ...

    • Self-Constructing Graph Convolutional Networks for Semantic Labeling 

      Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt-Børre (Chapter, 2020)
      Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the ...

    • Self-constructing graph neural networks to model long-range pixel dependencies for semantic segmentation of remote sensing images 

      Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt Børre (Journal article; Peer reviewed, 2021)
      Capturing global contextual representations in remote sensing images by exploiting long-range pixel-pixel dependencies has been shown to improve segmentation performance. However, how to do this efficiently is an open ...

    • The 1st Agriculture-Vision Challenge: Methods and Results 

      Chiu, Mang Tik; Xingqiang, Xu; Wang, Kai; Hobbs, Jennifer; Hovakimyan, Naira; Huang, Thomas S.; Shi, Honghui; Wei, Yunchao; Huang, Zilong; Schwing, Alexander; Brunner, Robert; Dozier, Ivan; Dozier, Wyatt; Ghandilyan, Karen; Wilson, David; Park, Hyunseong; Kim, Junhee; Kim, Sungho; Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt Børre; Barbosa, Alexandre; Trevisan, Rodrigo; Zhao, Bingchen; Yu, Shaozuo; Yang, Siwei; Wang, Yin; Sheng, Hao; Chen, Xiao; Su, Jingyi; Rajagopal, Ram; Ng, Andrew; Huynh, Van Thong; Kim, Soo-Hyung; Na, In-Seop; Baid, Ujjwal; Innani, Shubham; Dutande, Prasad; Baheti, Bhakti; Talbar, Sanjay; Tang, Jianyu (Chapter, 2020)