Search Results for author:
Found 3 papers, 1 papers with code
E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation
In this paper, we notice that the class weights of categories that tend to share many adjacent boundary pixels lack discrimination, thereby limiting the performance.
MSP : Refine Boundary Segmentation via Multiscale Superpixel
Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.
FBNet: Feature Balance Network for Urban-Scene Segmentation
In this paper, we present a novel add-on module, named Feature Balance Network (FBNet), to eliminate the feature camouflage in urban-scene segmentation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
