Edge-Guided Non-Local Fully Convolutional Network for Salient Object Detection

Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN-based methods still suffer from continuous striding and pooling operations leading to loss of spatial structure and blurred edges. To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge-guided feature learning for accurate salient object detection. In a specific, we extract hierarchical global and local information in FCN to incorporate non-local features for effective feature representations. To preserve good boundaries of salient objects, we propose a guidance block to embed edge prior knowledge into hierarchical feature maps. The guidance block not only performs feature-wise manipulation but also spatial-wise transformation for effective edge embeddings. Our model is trained on the MSRA-B dataset and tested on five popular benchmark datasets. Comparing with the state-of-the-art methods, the proposed method performance well on five datasets.

Automated summary

In this study, a novel Edge-guided Non-local FCN (ENFNet) model is proposed for accurate salient object detection, aiming to maintain the clear edge structure of salient objects. By extracting global and local information in the Fully Convolutional Neural Network (FCN) and incorporating non-local features for effective feature representations, as well as embedding edge prior knowledge to preserve good boundaries of salient objects, the proposed method performs well compared to state-of-the-art methods on five benchmark datasets.