Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function

Abstract

We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training phase and a refinement phase to increase the efficiency of the network.