Convolutional Edge Constraint-Based U-Net for Salient Object Detection
The salient object detection is receiving more and more attention from researchers. An accurate saliency map will be useful for subsequent tasks. However, in most saliency maps predicted by existing models, the objects regions are very blurred and the edges of objects are irregular. The reason is th...
Main Authors: | Le Han, Xuelong Li, Yongsheng Dong |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8689037/ |
Similar Items
-
A Convolutional Encoder-Decoder Network With Skip Connections for Saliency Prediction
by: Fei Qi, et al.
Published: (2019-01-01) -
Jazz Bass Transcription Using a U-Net Architecture
by: Jakob Abeßer, et al.
Published: (2021-03-01) -
Match Feature U-Net: Dynamic Receptive Field Networks for Biomedical Image Segmentation
by: Xiaofei Qin, et al.
Published: (2020-07-01) -
Skip Connection U-Net for White Matter Hyperintensities Segmentation From MRI
by: Jiong Wu, et al.
Published: (2019-01-01) -
Deep Neural Architectures for Medical Image Semantic Segmentation: Review
by: Muhammad Zubair Khan, et al.
Published: (2021-01-01)