Multi-scale Edge-Based U-Shape Network for Salient Object Detection

Deep-learning based salient object detection methods achieve great improvements. However, there are still problems existing in the predictions, such as blurry boundary and inaccurate location, which is mainly caused by inadequate feature extraction integration. In this paper, we propose a Multi-scale Edge-based U-shape Network (MEUN) to integrate various features at different scales better performance. To extract more useful information for prediction, Edge modules embedded each decoder units. Besides, additional down-sampling module alleviates location inaccuracy. Experimental results on four benchmark datasets demonstrate validity reliability of proposed method. also shows its superiority when compared with 15 state-of-the-art methods.