文献类型：期刊文献

英文题名：A novel deep network and aggregation model for saliency detection

作者：Liang, Ye[1];Liu, Hongzhe[1];Ma, Nan[2]

通讯作者：Liang, Y[1]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China.|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

年份：2020

卷号：36

期号：9

起止页码：1883-1895

外文期刊名：VISUAL COMPUTER

收录：;EI(收录号：20195107878411);Scopus(收录号：2-s2.0-85076576336);WOS:【SCI-EXPANDED(收录号:WOS:000541644600001)】；

基金：This work was supported in part by the National Natural Science Foundation of China (61871038, 61871039) and Beijing Natural Science Foundation (4182022).

语种：英文

外文关键词：Saliency detection; Multi-scale network; Feature pyramid; Saliency aggregation

摘要：Recent deep learning-based methods for saliency detection have proved the effectiveness of integrating features with different scales. They usually design various complex architectures of network, e.g., multiple networks, to explore the multi-scale information of images, which is expensive in computation and memory. Feature maps produced with different subsampling convolutional layers have different spatial resolutions; therefore, they can be used as the multi-scale features to reduce the costs. In this paper, by exploiting the in-network feature hierarchy of convolutional networks, we propose a novel multi-scale network for saliency detection (MSNSD) consisting of three modules, i.e., bottom-up feature extraction, top-down feature connection and multi-scale saliency prediction. Moreover, to further boost the performance of MSNSD, an input image-aware saliency aggregation method is proposed based on the ridge regression, which combines MSNSD with some well-performed handcrafted shallow models. Extensive experiments on several benchmarks show that the proposed MSNSD outperforms the state-of-the-art saliency methods with less computational and memory complexity. Meanwhile, our aggregation method for saliency detection is effective and efficient to combine deep and shallow models and make them complementary to each other.