ShapeConv

2000년 도입 · 논문 2편에서 사용

ShapeConv, or Shape-aware Convolutional layer, is a convolutional layer for processing the depth feature in indoor RGB-D semantic segmentation. The depth feature is firstly decomposed into a shape-component and a base-component, next two learnable weights are introduced to cooperate with them independently, and finally a convolution is applied on the re-weighted combination of these two components.

출처: ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

소개 논문: ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation