点击次数：

论文类型：期刊论文

发表时间：2020-01-01

发表刊物：IEEE TRANSACTIONS ON IMAGE PROCESSING

收录刊物：EI、SCIE

卷号：29

页面范围：3534-3545

ISSN号：1057-7149

关键字：Salient object detection; stagewise refinement; pyramid pooling module; layerwise recurrent; channel attention; global average pooling

摘要：Deep convolutional neural networks (CNNs) have been successfully applied to a wide variety of problems in computer vision, including salient object detection. To accurately detect and segment salient objects, it is necessary to extract and combine high-level semantic features with low-level fine details simultaneously. This is challenging for CNNs because repeated subsampling operations such as pooling and convolution lead to a significant decrease in the feature resolution, which results in the loss of spatial details and finer structures. Therefore, we propose augmenting feedforward neural networks by using the multistage refinement mechanism. In the first stage, a master net is built to generate a coarse prediction map in which most detailed structures are missing. In the following stages, the refinement net with layerwise recurrent connections to the master net is equipped to progressively combine local context information across stages to refine the preceding saliency maps in a stagewise manner. Furthermore, the pyramid pooling module and channel attention module are applied to aggregate different-region-based global contexts. Extensive evaluations over six benchmark datasets show that the proposed method performs favorably against the state-of-the-art approaches.