Salient object detection with pyramid attention and salient edges
This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions. The first is the exploitation of an essential pyramid attention structure for salient object detection. This enable...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2019
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sol_research/3161 https://ink.library.smu.edu.sg/context/sol_research/article/5119/viewcontent/Wang_Salient_Object_Detection_With_Pyramid_Attention_and_Salient_Edges_CVPR_2019_pvoa.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sol_research-5119 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sol_research-51192020-07-24T00:41:02Z Salient object detection with pyramid attention and salient edges WANG, Wenguan ZHAO, Shuyang SHEN, Jianbing HOI, Steven C. H. BORJI, Ali This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions. The first is the exploitation of an essential pyramid attention structure for salient object detection. This enables the network to concentrate more on salient regions while considering multi-scale saliency information. Such a stacked attention design provides a powerful tool to efficiently improve the representation ability of the corresponding network layer with an enlarged receptive field. The second contribution lies in the emphasis on the importance of salient edges. Salient edge information offers a strong cue to better segment salient objects and refine object boundaries. To this end, our model is equipped with a salient edge detection module, which is learned for precise salient boundary estimation. This encourages better edge-preserving salient object segmentation. Exhaustive experiments confirm that the proposed pyramid attention and salient edges are effective for salient object detection. We show that our deep saliency model outperforms state-of-the-art approaches for several benchmarks with a fast processing speed (25fps on one GPU). 2019-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sol_research/3161 info:doi/10.1109/CVPR.2019.00154 https://ink.library.smu.edu.sg/context/sol_research/article/5119/viewcontent/Wang_Salient_Object_Detection_With_Pyramid_Attention_and_Salient_Edges_CVPR_2019_pvoa.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection Yong Pung How School Of Law eng Institutional Knowledge at Singapore Management University Image and Video Synthesis Low-level Vision Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Image and Video Synthesis Low-level Vision Databases and Information Systems |
spellingShingle |
Image and Video Synthesis Low-level Vision Databases and Information Systems WANG, Wenguan ZHAO, Shuyang SHEN, Jianbing HOI, Steven C. H. BORJI, Ali Salient object detection with pyramid attention and salient edges |
description |
This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions. The first is the exploitation of an essential pyramid attention structure for salient object detection. This enables the network to concentrate more on salient regions while considering multi-scale saliency information. Such a stacked attention design provides a powerful tool to efficiently improve the representation ability of the corresponding network layer with an enlarged receptive field. The second contribution lies in the emphasis on the importance of salient edges. Salient edge information offers a strong cue to better segment salient objects and refine object boundaries. To this end, our model is equipped with a salient edge detection module, which is learned for precise salient boundary estimation. This encourages better edge-preserving salient object segmentation. Exhaustive experiments confirm that the proposed pyramid attention and salient edges are effective for salient object detection. We show that our deep saliency model outperforms state-of-the-art approaches for several benchmarks with a fast processing speed (25fps on one GPU). |
format |
text |
author |
WANG, Wenguan ZHAO, Shuyang SHEN, Jianbing HOI, Steven C. H. BORJI, Ali |
author_facet |
WANG, Wenguan ZHAO, Shuyang SHEN, Jianbing HOI, Steven C. H. BORJI, Ali |
author_sort |
WANG, Wenguan |
title |
Salient object detection with pyramid attention and salient edges |
title_short |
Salient object detection with pyramid attention and salient edges |
title_full |
Salient object detection with pyramid attention and salient edges |
title_fullStr |
Salient object detection with pyramid attention and salient edges |
title_full_unstemmed |
Salient object detection with pyramid attention and salient edges |
title_sort |
salient object detection with pyramid attention and salient edges |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2019 |
url |
https://ink.library.smu.edu.sg/sol_research/3161 https://ink.library.smu.edu.sg/context/sol_research/article/5119/viewcontent/Wang_Salient_Object_Detection_With_Pyramid_Attention_and_Salient_Edges_CVPR_2019_pvoa.pdf |
_version_ |
1770575313634328576 |