2,933 Hits in 8.7 sec

Deep Edge-Aware Saliency Detection [article]

Jing Zhang, Yuchao Dai, Fatih Porikli, Mingyi He
2017 arXiv   pre-print
In this paper, we tackle these issues by a new fully convolutional neural network that jointly learns salient edges and saliency labels in an end-to-end fashion.  ...  compositions, multiple salient objects, and salient objects of diverse scales.  ...  To tackle the above challenges, we propose a fully convolutional neural network (FCN) and an end-to-end learning framework for edge-aware saliency detection, as depicted in Fig. 2 .  ... 
arXiv:1708.04366v1 fatcat:dnqdqph7drfpjpbfpxvkag7szi

Edge-guided Non-local Fully Convolutional Network for Salient Object Detection [article]

Zhengzheng Tu, Yan Ma, Chenglong Li, Jin Tang, Bin Luo
2019 arXiv   pre-print
Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN based methods still suffer from  ...  To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge guided feature learning for accurate salient object detection.  ...  [30] propose to train two deep neural networks to integrate global search and local estimation for salient object detection.  ... 
arXiv:1908.02460v2 fatcat:e7sjjjwpfbh6roglc4ujrjae5e

EGNet:Edge Guidance Network for Salient Object Detection [article]

Jia-Xing Zhao and Jiangjiang Liu and Den-Ping Fan and Yang Cao and Jufeng Yang and Ming-Ming Cheng
2019 arXiv   pre-print
Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries.  ...  Accordingly, we present an edge guidance network (EGNet) for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network.  ...  Recently, convolutional neural networks (CNNs) [25] have successfully broken the limits of traditional handcrafted features, especially after the emerging of Fully Convolutional Neural Networks (FCNs  ... 
arXiv:1908.08297v1 fatcat:m6r4dknszva6zc5cbpkm5g7drm

Salient Contour-Aware Based Twice Learning Strategy for Saliency Detection

Chunbiao Zhu, Wei Yan, Shan Liu, Thomas Li, Ge Li
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
Fully convolutional neural networks (FCNs) have shown outstanding performance in many computer vision tasks including salient object detection.  ...  However, most deep learning-based saliency detection models are too complicated. They cause difficulties in training.  ...  We should control the learning process of neural network, and gradually obtain the results of salient object detection.  ... 
doi:10.1109/iccvw.2019.00311 dblp:conf/iccvw/ZhuYLLL19 fatcat:i4fhhtsycbaztabwsjd63iew2e

Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation

Heyi Li, Yunke Tian, Klaus Mueller, Xin Chen
2019 Image and Vision Computing  
Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge.  ...  As such, our proposed SR map constitutes a convenient visual interface which unveils the visual attention of the network and reveals which type of objects the model has learned to recognize after training  ...  The context-aware saliency detection algorithm extracts salient objects in the image together with their meaningful surroundings.  ... 
doi:10.1016/j.imavis.2019.02.005 fatcat:4gumh6ftkjgkxfr7q3ktg63epq

ESPFNet: An Edge-aware Spatial Pyramid Fusion Network for Salient Shadow Detection in Aerial Remote Sensing Images

Shuang Luo, Huifang Li, Ruzhao Zhu, Yuting Gong, Huanfeng Shen
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this work, a novel edge-aware spatial pyramid fusion network (ESPFNet) under a multi-task learning framework is proposed for salient shadow detection in aerial remote sensing images.  ...  ESPFNet has three components: 1) a parallel spatial pyramid (PSP) structure; 2) an edge detection module (EDM); and 3) an edge-aware multi-branch integration (EMI).  ...  A deeply supervised convolutional neural network for shadow detection (DSSDNet) was also proposed at the same time.  ... 
doi:10.1109/jstars.2021.3066791 fatcat:76fvjk7zxbdrncwmoqaurgynta

Salient Object Detection With Pyramid Attention and Salient Edges

Wenguan Wang, Shuyang Zhao, Jianbing Shen, Steven C. H. Hoi, Ali Borji
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, makes two major novel contributions.  ...  Such a salient edge detection module learns for precise salient boundary estimation, and thus encourages better edge-preserving salient object segmentation.  ...  A readout network R for detecting salient objects is then learned using both the saliency feature Y and explicit salient edge information from F.  ... 
doi:10.1109/cvpr.2019.00154 dblp:conf/cvpr/WangZSHB19 fatcat:rc6anlb3fjb4tj5h64ljjcbg4a

Cross refinement network with edge detection for salient object detection

Junjiang Xiang, Xiao Hu, Jiayu Ding, Xiangyue Tan, Jiaxin Yang
2021 IET Signal Processing  
modules and four edge-salient cross units; and a detection network with an edge enhancement unit and a residual refinement network (RNN).  ...  To solve these problems, this article proposes the novel cross refinement network, which consists of a Res2Net-based backbone network; a fusion network equipped with four convolutional block attention  ...  To mitigate missing objects and blurred boundaries in salient detection, existing SOD methods can be classified into three categories: feature aggregation-based methods, edge-aware-based methods, and attention-based  ... 
doi:10.1049/sil2.12041 fatcat:eljmpaxoujeqhcmlntn2id5cae

Dynamic Message Propagation Network for RGB-D Salient Object Detection [article]

Baian Chen, Zhilei Chen, Xiaowei Hu, Jun Xu, Haoran Xie, Mingqiang Wei, Jing Qin
2022 arXiv   pre-print
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring  ...  To achieve this, we formulate a dynamic message propagation (DMP) module with the graph neural networks and deformable convolutions to dynamically learn the context information and to automatically predict  ...  RELATED WORK In this section, we briefly review the related progress of RGB-D salient object detection and graph neural network in recent years. A.  ... 
arXiv:2206.09552v1 fatcat:rzcne743q5ewvedczwzkzkilo4

WFNet: A Wider and Finer Network for Salient Object Detection

Jun Cen, Han Sun, Xinyi Chen, Ningzhong Liu, Dong Liang, Huiyu Zhou
2020 IEEE Access  
Many CNN-based methods have been proposed to detect salient objects, which raise the performance of SOD to a new level especially after the emergence of Fully Convolutional Neural Network (FCN) [5] .  ...  EDGE-BASED MODELS Many methods based on U-Net architecture have been proposed to detect salient objects [20] [21] [22] .  ... 
doi:10.1109/access.2020.3039890 fatcat:cmyufuveb5c67bz5yvsih6o7t4

Enhanced Boundary Learning for Glass-like Object Segmentation [article]

Hao He, Xiangtai Li, Guangliang Cheng, Jianping Shi, Yunhai Tong, Gaofeng Meng, Véronique Prinet, Lubin Weng
2021 arXiv   pre-print
We then introduce an edge-aware point-based graph convolution network module to model the global shape along the boundary.  ...  Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping.  ...  Cascaded partial de- V-net: Fully convolutional neural networks for volumetric coder for fast and accurate salient object detection. In CVPR, medical image segmentation. In 3DV.  ... 
arXiv:2103.15734v2 fatcat:icamf6wbzzbx7nwnbc4da3tqdy

Contour-aware Recurrent Cross Constraint Network for Salient Object Detection

Cuili Yao, Yuqiu Kong, Lin Feng, Bo Jin, Hui Si
2020 IEEE Access  
CONTOUR-AWARE SALIENT OBJECT DETECTION The SOD method based on deep learning has achieved satisfactory performance, especially when employing FCNs.  ...  Recently, fully convolutional neural networks (FCNs) [15] , [16] have been successfully adopted for SOD.  ... 
doi:10.1109/access.2020.3042203 fatcat:d6lqogialneh5iuifty7mrfryu

SODA2:Salient Object Detection with Structure-adaptive & Scale-adaptive Receptive Field

Jing. Liu, Han. Wang, Changfei. Yan, Min. Yuan, Yuting. Su
2020 IEEE Access  
Noticing the deficiency of single-feature-based methods, recent methods fused multiple features from Deep Neural Networks (DNNs) and obtained better performance thanks to the hierarchical feature representations  ...  Salient objects with complex shapes and arbitrary sizes are generally hard to detect, especially in cluttered background and complex scenes.  ...  RECEPTIVE FILED As mentioned by many existing works, salient object detection is highly context-aware where salient objects usually have obvious differences from their surroundings (e.g., colors) to pop  ... 
doi:10.1109/access.2020.3036638 fatcat:muy5yyghnzc2vadgxq3ybg7waq

VCIP 2020 Index

2020 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)  
Wu, Yang GRNet: Deep Convolutional Neural Networks based on Graph Reasoning for Semantic Segmentation T X Xia, Sifeng Sensitivity-Aware Bit Allocation for Intermediat Deep Feature Compression  ...  Spatial-Channel Context-Based Entropy Modeling for End-to-end Optimized Image Compression Li, Chun-Guang Learning Convolution Feature Aggregation via Edge Attention Convolution Network for Perso  ... 
doi:10.1109/vcip49819.2020.9301896 fatcat:bdh7cuvstzgrbaztnahjdp5s5y

A Fusion Model for Saliency Detection Based on Semantic Soft Segmentation

Jie Tao, Yaocai Wu, Xiaolong Zhou, Qike Shao, Sixian Chan
2022 Electronics  
Most deep saliency detection algorithms are based on convolutional neural networks, which still have great room for improvement in the edge accuracy of salient objects recognition, which may lead to fuzzy  ...  With the rapid development of neural networks in recent years, saliency detection based on deep learning has made great breakthroughs.  ...  In addition to the application of convolutional neural networks, researchers have also introduced a variety of different algorithms, such as saliency detection based on fully convolutional neural network  ... 
doi:10.3390/electronics11172712 fatcat:m6kkmeq6cjdfrkzgxv45ti7hya
« Previous Showing results 1 — 15 out of 2,933 results