1,297 Hits in 7.7 sec

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
2020 Entropy  
Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection.  ...  Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.  ...  This enables the network to integrate the multi-scale contexts over time and also, provide semantic cues to lower layers for better feature refinement.  ... 
doi:10.3390/e22101174 pmid:33286942 pmcid:PMC7597345 fatcat:3p5d2nal4vhxbi2via3g7oicga

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

Jing. Liu, Han. Wang, Changfei. Yan, Min. Yuan, Yuting. Su
2020 IEEE Access  
Salient objects with complex shapes and arbitrary sizes are generally hard to detect, especially in cluttered background and complex scenes.  ...  Upon the structureadaptive features on different semantic level, novel spatial context-aware modules (SCAMs) are devised to capture multi-scale contexts with dilated convolutions of deliberately designed  ...  SODA 2 is faster than the other methods, achieving a real-time speed of 33.7 FPS which can meet the real-time requirements of most vision tasks. D.  ... 
doi:10.1109/access.2020.3036638 fatcat:muy5yyghnzc2vadgxq3ybg7waq

Contour-aware Recurrent Cross Constraint Network for Salient Object Detection

Cuili Yao, Yuqiu Kong, Lin Feng, Bo Jin, Hui Si
2020 IEEE Access  
It consisted of a densely supervised encoder-decoder network for coarse saliency prediction and a residual module for saliency map refinement by learning the residuals between the coarse saliency map and  ...  [36] presented an accurate yet compact deep network that can enable real-time applications.  ... 
doi:10.1109/access.2020.3042203 fatcat:d6lqogialneh5iuifty7mrfryu

Multi-scale iterative refinement network for RGB-D salient object detection

Ze-yu Liu, Jian-wei Liu, Xin Zuo, Ming-fei Hu
2021 Engineering applications of artificial intelligence  
Cross-modal fusion and multi-scale refinement are still an open problem in RGB-D salient object detection task.  ...  The extensive research leveraging RGB-D information has been exploited in salient object detection.  ...  to produce saliency map. [26] incorporates object level semantics and global context to enforce the network to mimic eye fixations.  ... 
doi:10.1016/j.engappai.2021.104473 fatcat:2dj6azts2fajlju7c55mnpw5sq

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

Zhou Huang, Huaixin Chen, Biyuan Liu, Zhixi Wang
2021 Remote Sensing  
This paper explores the inherent properties of multi-level features to develop a novel semantic-guided attention refinement network (SARNet) for SOD of NSI.  ...  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  ...  Acknowledgments: The authors would like to thank Dengping Fan for his guidance and help in this work. Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/rs13112163 fatcat:syufwr2xhnh3nchgftmjile6hi

Saliency-Guided Attention Network for Image-Sentence Matching [article]

Zhong Ji, Haoran Wang, Jungong Han, Yanwei Pang
2021 arXiv   pre-print
Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules.  ...  This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge.  ...  Saliency-weighted Visual Attention (SVA) The Residual Refinement Saliency Network Various approaches [16, 44, 13] have been studied for visual saliency detection.  ... 
arXiv:1904.09471v4 fatcat:zmukwaqu2ja5do7mgr3cxev3yi

MPI: Multi-receptive and Parallel Integration for Salient Object Detection [article]

Han Sun, Jun Cen, Ningzhong Liu, Dong Liang, Huiyu Zhou
2021 arXiv   pre-print
The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's  ...  In this paper, a novel method called MPI is proposed for salient object detection.  ...  [16] designs an accurate and compact deep SOD network, it first employs residual learning to learn side-output residual features for saliency refinement, then the reverse attention is used to guide  ... 
arXiv:2108.03618v1 fatcat:ek7dosr4vnckxdz45qmpe5r4iq

CAGNet: Content-Aware Guidance for Salient Object Detection [article]

Sina Mohammadi, Mehrdad Noori, Ali Bahri, Sina Ghofrani Majelan, Mohammad Havaei
2019 arXiv   pre-print
Beneficial from Fully Convolutional Neural Networks (FCNs), saliency detection methods have achieved promising results.  ...  However, it is still challenging to learn effective features for detecting salient objects in complicated scenarios, in which i) non-salient regions may have "salient-like" appearance; ii) the salient  ...  [29] propose multi-context CNNs for exploiting local and global context for salient object detection.  ... 
arXiv:1911.13168v1 fatcat:cgskglb7mjgsln52jei26ku2xe

Revise-Net: Exploiting Reverse Attention Mechanism for Salient Object Detection

Rukhshanda Hussain, Yash Karbhari, Muhammad Fazal Ijaz, Marcin Woźniak, Pawan Kumar Singh, Ram Sarkar
2021 Remote Sensing  
Recently, deep learning-based methods, especially utilizing fully convolutional neural networks, have shown extraordinary performance in salient object detection.  ...  Despite its success, the clean boundary detection of the saliency objects is still a challenging task.  ...  A Simple Pooling-Based Design for Real-Time Salient Object Detection.  ... 
doi:10.3390/rs13234941 fatcat:4jno22evrvehbm4zznwfi43yp4

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
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.  ...  However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning.  ...  Deep high-resolution represen- saliency network for salient object detection. In CVPR, 2016. tation learning for visual recognition.  ... 
arXiv:2103.15734v2 fatcat:icamf6wbzzbx7nwnbc4da3tqdy

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
Li, F., +, TIP 2020 7045-7060 Residual Learning for Salient Object Detection.  ...  ., +, TIP 2020 8177-8186 Context-Integrated and Feature-Refined Network for Lightweight Object Parsing.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Hybrid Local and Global Deep-Learning Architecture for Salient-Object Detection

Wajeeha Sultan, Nadeem Anjum, Mark Stansfield, Naeem Ramzan
2020 Applied Sciences  
Salient-object detection is a fundamental and the most challenging problem in computer vision. This paper focuses on the detection of salient objects, especially in low-contrast images.  ...  Experimentation was performed on five standard datasets, and results were compared with state-of-the-art approaches.  ...  To overcome these problems, we propose a boundary-aware fully convolutional network for the detection of salient objects that captures both the local and global context with a built-in refinement module  ... 
doi:10.3390/app10238754 fatcat:w4poi5kk2zffzhhyqwhzjfslii

Deep Edge-Aware Saliency Detection [article]

Jing Zhang, Yuchao Dai, Fatih Porikli, Mingyi He
2017 arXiv   pre-print
levels of the deep network to leverage available information for multi-scale response, and finally refines the saliency map through dilated convolutions by imposing context.  ...  There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex  ...  Context Module for Saliency Refinement Using our deep-shallow model, we produce a dense saliency map.  ... 
arXiv:1708.04366v1 fatcat:dnqdqph7drfpjpbfpxvkag7szi

PGCA-Net: Progressively Aggregating Hierarchical Features with the Pyramid Guided Channel Attention for Saliency Detection

Jiajie Mai, Xuemiao Xu, Guorong Xiao, Zijun Deng, Jiaxing Chen
2020 Intelligent Automation and Soft Computing  
Hou et al. ( 2017 ) proposed a network with deep supervision and detailed features for saliency detection.  ...  The stochastic gradient descent (SGD), is utilized to adjust the network for 10,000 times.  ...  Deeply supervised salient object detection with short connections. In Proceedings of the IEEE Conference on Computer . Hu, J., Shen, L., & Sun, G. (2018) . Squeeze-andexcitation networks.  ... 
doi:10.32604/iasc.2020.010119 fatcat:3odd64j5qrdwbm554ululxjy2a

CGNet: cross-guidance network for semantic segmentation

Zhijie Zhang, Yanwei Pang
2020 Science China Information Sciences  
The issue of semantic segmentation is to extract discriminative features for distinguishing different objects and recognizing hard examples.  ...  The edge and saliency detection network are unified into the CGNet, and model the intrinsic information among them, guiding the process of extracting discriminative features.  ...  network for semantic segmentation.  ... 
doi:10.1007/s11432-019-2718-7 fatcat:7u4tqfavfrg4xmtzedktyglegu
« Previous Showing results 1 — 15 out of 1,297 results