点击次数：

论文类型：期刊论文

发表时间：2018-10-27

发表刊物：NEUROCOMPUTING

收录刊物：SCIE

卷号：312

页面范围：229-238

ISSN号：0925-2312

关键字：Saliency detection; Convolutional neural networks; Multi-task learning

摘要：Category-independent region proposals have been utilized for salient objects detection in recent works. However, these works may fail when the extracted proposals have poor overlap with salient objects. In this paper, we demonstrate segment-level saliency prediction can provide these methods with complementary information to improve detection results. In addition, classification loss (i.e., softmax) can distinguish positive samples from negative ones and similarity loss (i.e., triplet) can enlarge the contrast difference between samples with different class labels. We propose a joint optimization of the two losses to further promote the performance. Finally, a multi-layer cellular automata model is incorporated to generate the final saliency map with fine shape boundary and object-level highlighting. The proposed method has achieved state-of-the-art results on four benchmark datasets. (C) 2018 Elsevier B.V. All rights reserved.