A novel approach for visual Saliency detection and segmentation based on objectness and top-down attention
Xu Yang, Jun Li, Jianbin Chen, Guangtian Shen, Yangjian Gao · 2017
Visual saliency detection is usually a prerequisite for image processing tasks like object segmentation, object recognition and information compression. In this work, we first present a novel method that combines cognitive-based objectness and image-based saliency to obtain a better saliency map with less negligible background information. Then, by introducing some top-down attention priors, we further propose a computational selective attention model for object segmentation task on the saliency map. Experiments have shown that our method obviously refines the saliency map of several state-of-the-art algorithms, and our selective attention model meanwhile evidently improves salient object segmentation performance in the challenging saliency benchmark-Extend Complex Scene Saliency Dataset (ECSSD).