Edge Distraction-aware Salient Object Detection

Integrating low-level edge features has been proven to be effective in preserving clear boundaries of salient objects. However, the locality of edge features makes it difficult to capture globally salient edges, leading to distraction in the final predictions. To address this problem, we propose to...

Full description

Saved in:
Bibliographic Details
Main Authors: REN, Sucheng, LIU, Wenxi, JIAO, Jianbo, HAN, Guoqiang, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8273
https://ink.library.smu.edu.sg/context/sis_research/article/9276/viewcontent/Edge_Distraction_aware_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9276
record_format dspace
spelling sg-smu-ink.sis_research-92762023-11-10T08:44:04Z Edge Distraction-aware Salient Object Detection REN, Sucheng LIU, Wenxi JIAO, Jianbo HAN, Guoqiang HE, Shengfeng Integrating low-level edge features has been proven to be effective in preserving clear boundaries of salient objects. However, the locality of edge features makes it difficult to capture globally salient edges, leading to distraction in the final predictions. To address this problem, we propose to produce distraction-free edge features by incorporating cross-scale holistic interdependencies between high-level features. In particular, we first formulate our edge features extraction process as a boundary-filling problem. In this way, we enforce edge features to focus on closed boundaries instead of those disconnected background edges. Second, we propose to explore cross-scale holistic contextual connections between every position pair of high-level feature maps regardless of their distances across different scales. It selectively aggregates features at each position based on its connections to all the others, simulating the "contrast" stimulus of visual saliency. Finally, we present a complementary features integration module to fuse low- and high-level features according to their properties. Experimental results demonstrate our proposed method outperforms previous state-of-the-art methods on the benchmark datasets, with the fast inference speed of 30 FPS on a single GPU. 2023-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8273 info:doi/10.1109/MMUL.2023.3235936 https://ink.library.smu.edu.sg/context/sis_research/article/9276/viewcontent/Edge_Distraction_aware_av.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Feature extraction Image edge detection Object detection Visualization Filling Task analysis Convolution Graphics and Human Computer Interfaces Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Feature extraction
Image edge detection
Object detection
Visualization
Filling
Task analysis
Convolution
Graphics and Human Computer Interfaces
Software Engineering
spellingShingle Feature extraction
Image edge detection
Object detection
Visualization
Filling
Task analysis
Convolution
Graphics and Human Computer Interfaces
Software Engineering
REN, Sucheng
LIU, Wenxi
JIAO, Jianbo
HAN, Guoqiang
HE, Shengfeng
Edge Distraction-aware Salient Object Detection
description Integrating low-level edge features has been proven to be effective in preserving clear boundaries of salient objects. However, the locality of edge features makes it difficult to capture globally salient edges, leading to distraction in the final predictions. To address this problem, we propose to produce distraction-free edge features by incorporating cross-scale holistic interdependencies between high-level features. In particular, we first formulate our edge features extraction process as a boundary-filling problem. In this way, we enforce edge features to focus on closed boundaries instead of those disconnected background edges. Second, we propose to explore cross-scale holistic contextual connections between every position pair of high-level feature maps regardless of their distances across different scales. It selectively aggregates features at each position based on its connections to all the others, simulating the "contrast" stimulus of visual saliency. Finally, we present a complementary features integration module to fuse low- and high-level features according to their properties. Experimental results demonstrate our proposed method outperforms previous state-of-the-art methods on the benchmark datasets, with the fast inference speed of 30 FPS on a single GPU.
format text
author REN, Sucheng
LIU, Wenxi
JIAO, Jianbo
HAN, Guoqiang
HE, Shengfeng
author_facet REN, Sucheng
LIU, Wenxi
JIAO, Jianbo
HAN, Guoqiang
HE, Shengfeng
author_sort REN, Sucheng
title Edge Distraction-aware Salient Object Detection
title_short Edge Distraction-aware Salient Object Detection
title_full Edge Distraction-aware Salient Object Detection
title_fullStr Edge Distraction-aware Salient Object Detection
title_full_unstemmed Edge Distraction-aware Salient Object Detection
title_sort edge distraction-aware salient object detection
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8273
https://ink.library.smu.edu.sg/context/sis_research/article/9276/viewcontent/Edge_Distraction_aware_av.pdf
_version_ 1783955662585200640