MSDNN: Multi-Scale Deep Neural Network for Salient Object Detection
This work addresses the problem of salient object detection in computer vision, which is incremental as it builds on existing deep learning methods with a novel multi-scale approach.
The authors tackled salient object detection by proposing a multi-scale deep neural network (MSDNN) that extracts global features with RCNN and uses deconvolutional layers and a fusion module to generate saliency maps, achieving significant outperformance over 12 state-of-the-art approaches on four benchmark datasets.
Salient object detection is a fundamental problem and has been received a great deal of attentions in computer vision. Recently deep learning model became a powerful tool for image feature extraction. In this paper, we propose a multi-scale deep neural network (MSDNN) for salient object detection. The proposed model first extracts global high-level features and context information over the whole source image with recurrent convolutional neural network (RCNN). Then several stacked deconvolutional layers are adopted to get the multi-scale feature representation and obtain a series of saliency maps. Finally, we investigate a fusion convolution module (FCM) to build a final pixel level saliency map. The proposed model is extensively evaluated on four salient object detection benchmark datasets. Results show that our deep model significantly outperforms other 12 state-of-the-art approaches.