转载请注明出处。
作者:Peng Sun Wenhu Zhang Huanyu Wang Songyuan Li Xi Li
2021CVPR
作者提出了一个具有深度敏感注意力和自动多模态融合的深度RGB-D显著性检测网络,主要创新在于提出了a depth-sensitive RGB feature modeling scheme using the depth-wise geometric prior of salient objects 和 an automatic architecture search approach 。
整个网络结构图的设计如下:
其中,The RGB branch 是基于VGG-19,the depth branch is a lightweight depth network。
网络设计的三个原则如下:
1)The features from different modalities of the same scale are always fused, while features in different scales are selectively fused.
2)Low-level features are always combined with high-level features before the fifinal prediction, as low-level features are rich in spatial details but lack