Filters








3,567 Hits in 4.6 sec

Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks [article]

Dominique Beaini, Sofiane Achiche, Alexandre Duperré, Maxime Raison
2019 arXiv   pre-print
The objective of this paper is to show that saliency convolutional neural networks (CNN) can be improved by using a Green's function convolution (GFC) to extrapolate edges features into salient regions  ...  A major contribution of the current work is the first implementation of Green's function convolution inside a neural network, which allows the network to operate in the feature domain and in the gradient  ...  Then, the Green function in the Fourier domain mono ℱ is given by (8) [20] . In equation (8) , mono ℱ is the Green's function that allows to solve any Laplacian by a convolution [20, 29] .  ... 
arXiv:1908.08331v2 fatcat:evoqhkzgibdp3bchxnxpffw2we

Understanding Saliency Prediction with Deep Convolutional Neural Networks and Psychophysical Models [article]

Qiang Li
2022 arXiv   pre-print
Convolutional neural networks (CNNs) have achieved great success in natural image saliency prediction.  ...  However, psychophysical models were more unstable in noise than pre-trained deep neural networks.  ...  It can improve the generality and stability of artificial neural networks, but there is insufficient research in this area.  ... 
arXiv:2204.06071v3 fatcat:mvddbj3sszfuvnwo23adanau34

Salient Object Detection in Video using Deep Non-Local Neural Networks [article]

Mohammad Shokri, Ahad Harati, Kimya Taba
2018 arXiv   pre-print
A novel deep non-local neural network architecture is introduced for video salient object detection and tested on two well-known datasets DAVIS and FBMS.  ...  In spite of the fact that the state of the art in saliency detection for still images has been changed substantially over the last few years, there have been few improvements in video saliency detection  ...  The re-emergence of convolutional neural networks (CNN) has brought about a signif-icant improvement in a wide range of computer vision areas.  ... 
arXiv:1810.07097v1 fatcat:usc6h26hvnfphohkzeamrwopxe

Deep Contrast Learning for Salient Object Detection [article]

Guanbin Li, Yizhou Yu
2016 arXiv   pre-print
Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs).  ...  In this CVPR 2016 paper, we propose an end-to-end deep contrast network to overcome the aforementioned limitations.  ...  [25] trained a deep neural network for deriving a saliency map from multiscale features extracted using deep convolutional neural networks. Wang et al.  ... 
arXiv:1603.01976v1 fatcat:6fzzvx7bbzchnoareblukqe2be

A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network [article]

Xuanyang Xi, Yongkang Luo, Fengfu Li, Peng Wang, Hong Qiao
2017 arXiv   pre-print
In this paper, we tackle this problem by proposing a fast and compact saliency score regression network which employs fully convolutional network, a special deep convolutional neural network, to estimate  ...  It is an extremely simplified end-to-end deep neural network without any pre-processings and post-processings.  ...  natural to consider convolutional neural networks for saliency detection.  ... 
arXiv:1702.00615v2 fatcat:k5cmdlt6m5audhjm4yzun52dum

Contrast-Oriented Deep Neural Networks for Salient Object Detection

Guanbin Li, Yizhou Yu
2018 IEEE Transactions on Neural Networks and Learning Systems  
Deep convolutional neural networks have become a key element in the recent breakthrough of salient object detection.  ...  Each of our deep networks is composed of two complementary components, including a fully convolutional stream for dense prediction and a segment-level spatial pooling stream for sparse saliency inference  ...  DEEP CONTRAST NETWORK As illustrated in Fig. 1 , our proposed contrast-oriented deep neural network is composed of two complementary components, a fully convolutional stream for dense saliency prediction  ... 
doi:10.1109/tnnls.2018.2817540 pmid:29993934 fatcat:fvchrcr6sfclfgmimhg75otw6u

Deep Contrast Learning for Salient Object Detection

Guanbin Li, Yizhou Yu
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs).  ...  In this paper, we propose an end-to-end deep contrast network to overcome the aforementioned limitations.  ...  [26] trained a deep neural network for deriving a saliency map from multiscale features extracted using deep convolutional neural networks. Wang et al.  ... 
doi:10.1109/cvpr.2016.58 dblp:conf/cvpr/LiY16 fatcat:ujctasozxnbj5kr3cfz6bi3e7y

Self-Attention Recurrent Network for Saliency Detection [article]

Fengdong Sun, Wenhui Li, Yuanyuan Guan
2018 arXiv   pre-print
Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results.  ...  In this paper, we propose a novel end-to-end deep saliency network which could effectively utilize multi-scale feature maps according to their characteristics.  ...  In summary, contributions of this paper are as followings: 1. We propose a novel end-to-end deep convolutional neural network for robust saliency detection. The network consists of two parts.  ... 
arXiv:1808.01634v1 fatcat:uk4mdoefyfashovg6re6fulu6y

Improving the Curvelet Saliency and Deep Convolutional Neural Networks for Diabetic Retinopathy Classification in Fundus Images

V. T. H. Tuyet, N. T. Binh, D. T. Tin
2022 Engineering, Technology & Applied Science Research  
This paper proposes a new method to classify diabetic retinopathy in retinal blood vessel images based on curvelet saliency for segmentation.  ...  To evaluate the results of the proposed method STARE and HRF datasets are used for testing with the Jaccard Index.  ...  www.etasr.com Tuyet et al.: Improving the Curvelet Saliency with Deep Convolutional Neural Networks for Diabetic … Fig. 4 . 4 Fig. 4. Segmentation result comparison in the HRF dataset.  ... 
doi:10.48084/etasr.4679 fatcat:tinmiwbvfzeflgay2nkzn74434

Saliency Maps-Based Convolutional Neural Networks for Facial Expression Recognition

Qinglan Wei
2021 IEEE Access  
INDEX TERMS Facial expression recognition, saliency maps, dilated convolution, prior knowledge, the convolutional neural network.  ...  With the prior knowledge of saliency maps and the multilayer deep features in the CNN network, the recognition accuracy is improved by obtaining more targeted and more complete deep expression information  ...  In recent years, the convolutional neural network (CNN) [3] model is one of the most popular methods used for FER tasks [4] .  ... 
doi:10.1109/access.2021.3082694 fatcat:kedvbskwy5ellbm3eq4p3vuyla

Estimating Attention of Faces Due to its Growing Level of Emotions

Ravi Kant Kumar, Jogendra Garain, Dakshina Ranjan Kisku, Goutam Sanyal
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
The concept of deep convolution neural network (CNN) has been applied for training and classification of different facial expression of emotions.  ...  In the literature of visual saliency authors have dealt with expressionless objects but it has not been addressed with object like face which exploits expressions.  ...  This is computed by deep convolution neural network (described in section 3 and 4).  ... 
doi:10.1109/cvprw.2018.00261 dblp:conf/cvpr/KumarGKS18 fatcat:3bv2dnzyzfdkrnpedjfdoljxe4

Visualization of Salient Object with Saliency Maps using Residual Neural Networks

Rubina Rashid, Saqib Ubaid, Muhammad Idrees, Rida Rafi, Imran Sarwar Bajwa
2021 IEEE Access  
"Deepfix: A fully convolutional neural network for predicting human eye fixations."  ...  INTRODUCTION The field of computer vision has taken a sensational curve, with the ascent of the Convolutional Neural Networks (CNNs), which is one of the most impressive form of Artificial Neural Networks  ... 
doi:10.1109/access.2021.3100155 fatcat:aqzrky7vhfbfbpwazj4fva2w2q

Pyramid Spatial Context Features for Salient Object Detection

Hui Li
2020 IEEE Access  
By further inserting this module in a deep network, namely PSCNet, we are able to optimize the network in an end-to-end manner for salient object detection.  ...  This paper presents a novel deep neural network design for salient object detection by formulating a pyramid spatial context module, PSC module for short, to capture the spatial context information at  ...  Next, we insert the PSC module in a deep convolutional neural network to build the PSCNet for salient object detection.  ... 
doi:10.1109/access.2020.2993572 fatcat:rigrimruubhbznb54ka4hoyb74

Convolutional Edge Constraint-Based U-Net for Salient Object Detection

Le Han, Xuelong Li, Yongsheng Dong
2019 IEEE Access  
Besides, the convolutional neural network (CNN)-based models predict saliency maps at patch scale, which causes the objects edges of the output to be fuzzy.  ...  Moreover, in order to better guide the network mining the information of objects edges, we design a new loss function based on image convolution, which adds an L1 constraint to the edge information of  ...  ACKNOWLEDGMENT This paper was presented in part at the Chinese Conference on Pattern Recognition and Computer Vision, Guangzhou, 2018. This paper was recommended by the program committee.  ... 
doi:10.1109/access.2019.2910572 fatcat:ottfbvrhxjahfez4j35ns4qbve

On Combining DeepSnake and Global Saliency for Detection of Orchard Apples

Wang Jing, Wang Leqi, Han Yanling, Zhang Yun, Zhou Ruyan
2021 Applied Sciences  
fruit regions in the saliency map.  ...  For the fast detection and recognition of apple fruit targets, based on the real-time DeepSnake deep learning instance segmentation model, this paper provided an algorithm basis for the practical application  ...  deep neural network, the data of each mini-bacth in the network normalized processing.  ... 
doi:10.3390/app11146269 fatcat:awvgswnwwzeuzogvtpbnyqcgqq
« Previous Showing results 1 — 15 out of 3,567 results