CoCNN: RGB-D deep fusion for stereoscopic salient object detection

作者：

Highlights：

• We develop a coupled CNN (CoCNN) architecture and present a systematic way to fuse multimodal and multiscale features for stereoscopic salient object detection.

• We propose a cascaded span network (CSN) that leverages a constrained span unit to fuse disparity and color cues and serves as a simple yet effective module for multimodal information fusion. This fusion method is able to mitigate the ambiguity of features from different modalities and enables the exploration of feature complementarity and correlations across different layers.

• The experimental results demonstrate that the proposed model outperforms other approaches. We verify the effectiveness of the proposed CSN through extensive experiments.

摘要

•We develop a coupled CNN (CoCNN) architecture and present a systematic way to fuse multimodal and multiscale features for stereoscopic salient object detection.•We propose a cascaded span network (CSN) that leverages a constrained span unit to fuse disparity and color cues and serves as a simple yet effective module for multimodal information fusion. This fusion method is able to mitigate the ambiguity of features from different modalities and enables the exploration of feature complementarity and correlations across different layers.•The experimental results demonstrate that the proposed model outperforms other approaches. We verify the effectiveness of the proposed CSN through extensive experiments.

论文关键词：Coupled CNN,Cascaded span network,Stereoscopic images,Salient object detection

论文评审过程：Received 12 July 2019, Revised 16 February 2020, Accepted 8 March 2020, Available online 9 March 2020, Version of Record 16 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107329