scholarly journals Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection

2018 ◽  
Vol 27 (1) ◽  
pp. 121-134 ◽  
Author(s):  
Xiang Wang ◽  
Huimin Ma ◽  
Xiaozhi Chen ◽  
Shaodi You
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Salient Object Detection ◽  
Salient Object ◽  
Edge Preserving ◽  
Multi Scale

scholarly journals Multi-scale deep neural network for salient object detection

2018 ◽  
Vol 12 (11) ◽  
pp. 2036-2041 ◽  
Author(s):  
Fen Xiao ◽  
Wenzheng Deng ◽  
Liangchan Peng ◽  
Chunhong Cao ◽  
Kai Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Deep Neural Network ◽  
Salient Object Detection ◽  
Salient Object ◽  
Multi Scale

Global Context Guided Multi-scale Feature Network for Salient Object Detection

2021 ◽  
pp. 81-89
Author(s):  
Zhenyu Zhao ◽  
Yachao Fang ◽  
Qing Zhang ◽  
Xiaowei Chen ◽  
Meng Dai ◽  
...  
Keyword(s):  
Object Detection ◽  
Salient Object Detection ◽  
Salient Object ◽  
Global Context ◽  
Scale Feature ◽  
Multi Scale

scholarly journals Salient Object Detection Based on Background Feature Clustering

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Kan Huang ◽  
Yong Zhang ◽  
Bo Lv ◽  
Yongbiao Shi
Keyword(s):  
Object Detection ◽  
Clustering Algorithm ◽  
Geodesic Distance ◽  
Saliency Map ◽  
Salient Object Detection ◽  
Salient Object ◽  
Edge Preserving ◽  
Feature Clustering ◽  
Background Distribution ◽  
Extensive Evaluation

Automatic estimation of salient object without any prior knowledge tends to greatly enhance many computer vision tasks. This paper proposes a novel bottom-up based framework for salient object detection by first modeling background and then separating salient objects from background. We model the background distribution based on feature clustering algorithm, which allows for fully exploiting statistical and structural information of the background. Then a coarse saliency map is generated according to the background distribution. To be more discriminative, the coarse saliency map is enhanced by a two-step refinement which is composed of edge-preserving element-level filtering and upsampling based on geodesic distance. We provide an extensive evaluation and show that our proposed method performs favorably against other outstanding methods on two most commonly used datasets. Most importantly, the proposed approach is demonstrated to be more effective in highlighting the salient object uniformly and robust to background noise.

Sign in / Sign up

Export Citation Format

Share Document