Multi-branch networks combine backbones whose inductive biases are complementary, but their fusion modules set the branch weights from feature statistics alone and are therefore blind to what a pixel represents. We supervise fusion in label space instead. Ground-truth labels are converted into per-pixel routing targets...
Inspired by human visual perception, where individuals first perceive an object globally and then focus on salient local details, the proposed hybrid CNN-Transformer architecture captures global representations and employs attention maps to refine task-relevant local features.
Abdulaziz Ali, Si-Yuan You, Li Li et al.· Applied intelligence (Boston...· 0 citations
A novel edge-aware transformer-based network, named RoofSeg, is developed for segmenting roof planes from LiDAR point clouds in a truly end-to-end manner and an Edge-Aware Mask Module (EAMM) is designed that sufficiently incorporates planar geometric prior of edges to enhance its discriminability for plane instance mas...
Si-Yuan You, Guo-Zheng Xu, Peng-Wei Zhou et al.· Isprs Journal of Photogramme...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.