MSDNN: Multi-Scale Deep Neural Network for Salient Object Detection
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2018
- DOI:
- 10.48550/arXiv.1801.04187
- arXiv:
- arXiv:1801.04187
- Bibcode:
- 2018arXiv180104187X
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- 10 pages, 12 figures