Edge-guided Non-local Fully Convolutional Network for Salient Object Detection
This work addresses edge preservation in salient object detection, which is important for applications like image segmentation, but it appears incremental as it builds on existing FCN methods with added guidance blocks.
The paper tackled the problem of blurred edges in salient object detection by proposing an Edge-guided Non-local FCN (ENFNet) that incorporates edge prior knowledge into feature maps, achieving state-of-the-art performance on five benchmark datasets.
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 achieves the best performance on all datasets.