文献类型：期刊文献

英文题名：Multi-level and multi-scale deep saliency network for salient object detection

作者：Zhang, Qing[1];Lin, Jiajun[2];Zhuge, Jingling[2];Yuan, Wenhao[3]

机构：[1]Shanghai Inst Technol, Coll Comp Sci & Informat Engn, Shanghai 201418, Peoples R China;[2]East China Univ Sci & Technol, Coll Informat Sci & Engn, Shanghai 200237, Peoples R China;[3]Shandong Univ Technol, Coll Comp Sci & Technol, Zibo 255000, Peoples R China

年份：2019

卷号：59

起止页码：415

外文期刊名：JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION

收录：;EI(收录号：20190606465291);WOS:【SCI-EXPANDED(收录号:WOS:000463462600044)】；

基金：This work is supported by the National Natural Science Foundation of China under Grant No. 61401281 and No. 61701286, and Science and Technology Development Foundation of Shanghai Institute of Technology under Grant No. ZQ2018-23.

语种：英文

外文关键词：Saliency detection; Salient object detection; Fully convolutional neural network; Multi-scale features

摘要：Traditional saliency model usually utilize handcrafted image features and various prior knowledge to pop out salient regions from complex surroundings. In this paper, we propose a novel FCN-like deep convolutional neural network for pixel-wise salient object detection. Our deep network automatically learns multi-level feature from different convolutional layers of a pre-trained convolutional neural network. Moreover, deeper side outputs are connected to the shallower ones, which provides a better feature representation and helps shallow side outputs to accurately locate salient regions. In addition, we adopt a weighted-fusion module to combine different side outputs for utilizing multi-scale and multi-level features. Finally, a fully connected CRF model can be optimally incorporated to improve spatial coherence and contour localization in the fused saliency map. Both qualitative and quantitative evaluations on four publicly available datasets demonstrate the robustness and efficiency of our proposed approach against 17 state-of-the-art methods. (C) 2019 Elsevier Inc. All rights reserved.