Paper Info
Title
Focal Boundary Guided Salient Object Detection
Abstract
The performance of salient object segmentation has been significantly advanced by using the deep convolutional networks. However, these networks often produce blob-like saliency maps without accurate object boundaries. This is caused by the limited spatial resolution of their feature maps after multiple pooling operations and might hinder downstream applications that require precise object shapes. To address this issue, we propose a novel deep model—Focal Boundary Guided (Focal-BG) network. Our model is designed to jointly learn to segment salient object masks and detect salient object boundaries. Our key idea is that additional knowledge about object boundaries can help to precisely identify the shape of the object. Moreover, our model incorporates a refinement pathway to refine the mask prediction and makes use of the focal loss to facilitate the learning of the hard boundary pixels. To evaluate our model, we conduct extensive experiments. Our Focal-BG network consistently outperforms the state-of-the-art methods on five major benchmarks. We provide a detailed analysis of these results and demonstrate that our joint modeling of salient object boundary and mask helps to better capture the shape details, especially in the vicinity of object boundaries.
Year
DOI
Venue
2019
10.1109/TIP.2019.2891055
IEEE Transactions on Image Processing
Keywords
Field
DocType
Object segmentation,Shape,Decoding,Task analysis,Saliency detection,Image segmentation,Feature extraction
Computer vision,Pattern recognition,Salience (neuroscience),Segmentation,Pooling,Image segmentation,Feature extraction,Artificial intelligence,Pixel,Deep learning,Image resolution,Mathematics
Journal
Volume
Issue
ISSN
28
6
1057-7149
Citations 
PageRank 
References 
5
0.46
9
Authors
5
Name
Order
Citations
PageRank
Yupei Wang1131.97
Xin Zhao213917.21
Xuecai Hu3151.94
Yin Li479735.85
Kaiqi Huang51931118.74