Multi-level Features Selection Network Based on Multi-attention for Salient Object Detection

2021 ◽  
pp. 315-326
Author(s):  
Jianyi Ren ◽  
Zheng Wang ◽  
Meijun Sun
Keyword(s):  
Object Detection ◽  
Salient Object Detection ◽  
Features Selection ◽  
Salient Object ◽  
Multi Level

Multi-level and multi-scale deep saliency network for salient object detection

2019 ◽  
Vol 59 ◽  
pp. 415-424 ◽  
Author(s):  
Qing Zhang ◽  
Jiajun Lin ◽  
JingJing Zhuge ◽  
Wenhao Yuan
Keyword(s):  
Object Detection ◽  
Salient Object Detection ◽  
Salient Object ◽  
Multi Scale ◽  
Multi Level

scholarly journals Unsupervised Salient Object Detection by Aggregating Multi-Level Cues

2018 ◽  
Vol 10 (6) ◽  
pp. 1-11
Author(s):  
Chenxing Xia ◽  
Hanling Zhang
Keyword(s):  
Object Detection ◽  
Salient Object Detection ◽  
Salient Object ◽  
Multi Level

scholarly journals Multi-Level Context Aggregation Network With Channel-Wise Attention for Salient Object Detection

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 102303-102312
Author(s):  
Zihui Jia ◽  
Zhenyu Weng ◽  
Fang Wan ◽  
Yuesheng Zhu
Keyword(s):  
Object Detection ◽  
Salient Object Detection ◽  
Salient Object ◽  
Multi Level

scholarly journals Semantic-Guided Attention Refinement Network for Salient Object Detection in Optical Remote Sensing Images

2021 ◽  
Vol 13 (11) ◽  
pp. 2163
Author(s):  
Zhou Huang ◽  
Huaixin Chen ◽  
Biyuan Liu ◽  
Zhixi Wang
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Network Architecture ◽  
Salient Object Detection ◽  
Optical Remote Sensing ◽  
Salient Object ◽  
Remote Sensing Images ◽  
Multi Level ◽  
Object Area ◽  
High Level

Although remarkable progress has been made in salient object detection (SOD) in natural scene images (NSI), the SOD of optical remote sensing images (RSI) still faces significant challenges due to various spatial resolutions, cluttered backgrounds, and complex imaging conditions, mainly for two reasons: (1) accurate location of salient objects; and (2) subtle boundaries of salient objects. This paper explores the inherent properties of multi-level features to develop a novel semantic-guided attention refinement network (SARNet) for SOD of NSI. Specifically, the proposed semantic guided decoder (SGD) roughly but accurately locates the multi-scale object by aggregating multiple high-level features, and then this global semantic information guides the integration of subsequent features in a step-by-step feedback manner to make full use of deep multi-level features. Simultaneously, the proposed parallel attention fusion (PAF) module combines cross-level features and semantic-guided information to refine the object’s boundary and highlight the entire object area gradually. Finally, the proposed network architecture is trained through an end-to-end fully supervised model. Quantitative and qualitative evaluations on two public RSI datasets and additional NSI datasets across five metrics show that our SARNet is superior to 14 state-of-the-art (SOTA) methods without any post-processing.

scholarly journals F³Net: Fusion, Feedback and Focus for Salient Object Detection

2020 ◽  
Vol 34 (07) ◽  
pp. 12321-12328 ◽  
Author(s):  
Jun Wei ◽  
Shuhui Wang ◽  
Qingming Huang
Keyword(s):  
Object Detection ◽  
Feature Fusion ◽  
Receptive Fields ◽  
Feedback Mechanism ◽  
Salient Object Detection ◽  
Salient Object ◽  
Structure Information ◽  
Multi Stage ◽  
Benchmark Datasets ◽  
Multi Level

Most of existing salient object detection models have achieved great progress by aggregating multi-level features extracted from convolutional neural networks. However, because of the different receptive fields of different convolutional layers, there exists big differences between features generated by these layers. Common feature fusion strategies (addition or concatenation) ignore these differences and may cause suboptimal solutions. In this paper, we propose the F3Net to solve above problem, which mainly consists of cross feature module (CFM) and cascaded feedback decoder (CFD) trained by minimizing a new pixel position aware loss (PPA). Specifically, CFM aims to selectively aggregate multi-level features. Different from addition and concatenation, CFM adaptively selects complementary components from input features before fusion, which can effectively avoid introducing too much redundant information that may destroy the original features. Besides, CFD adopts a multi-stage feedback mechanism, where features closed to supervision will be introduced to the output of previous layers to supplement them and eliminate the differences between features. These refined features will go through multiple similar iterations before generating the final saliency maps. Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details. Hard pixels from boundaries or error-prone parts will be given more attention to emphasize their importance. F3Net is able to segment salient object regions accurately and provide clear local details. Comprehensive experiments on five benchmark datasets demonstrate that F3Net outperforms state-of-the-art approaches on six evaluation metrics. Code will be released at https://github.com/weijun88/F3Net.

Sign in / Sign up

Export Citation Format

Share Document