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

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 2; pp. 582 - 593
• Main Authors: Tu, Zhengzheng, Ma, Yan, Li, Chenglong, Tang, Jin, Luo, Bin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Context modeling; Convolution; Datasets; Deep learning; edge guidance; Feature extraction; Feature maps; fully convolutional neural network; Image edge detection; Machine learning; non-local features; Object detection; Object recognition; Salience; Saliency detection; Salient object detection
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2020.2980853

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.