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.
@article{arxiv.1801.04187,
title = {MSDNN: Multi-Scale Deep Neural Network for Salient Object Detection},
author = {Fen Xiao and Wenzheng Deng and Liangchan Peng and Chunhong Cao and Kai Hu and Xieping Gao},
journal= {arXiv preprint arXiv:1801.04187},
year = {2018}
}