Collaborative multicue fusion using the cross-diffusion process for salient object detection

Salient object detection is very useful in a large variety of image and vision-related applications. A recent trend in salient object detection is to explore novel top-down visual cues and combine them with bottom-up saliency to improve the performance. However, a basic and important problem, i.e., how to effectively fuse multiple visual cues, has rarely been addressed in previous works. To this end, the paper presents a multicue fusion method using the cross-diffusion process (CDP) for salient object detection. The CDP algorithm is deployed to combine the affinity matrices constructed over individual visual cue channels, which is then embedded into a saliency propagation framework to accomplish salient object detection. Different from other multicue fusion strategies, our proposed approach allows for collaborative fusion, that is, the individual visual cues to be fused are able to interact and exchange information with each other during the fusion procedure, which can possibly correct the noise or corruption included in the individual visual cue channels, leading to more robust and effective fusion results. Intensive experiments on publicly available datasets demonstrate the effectiveness and superior performance of our proposed method.