Recurrent reverse attention guided residual learning for saliency object detection

Li, Tengpeng; Song, Hwangjun; Zhang, Kaihua; Liu, Qingshan

doi:10.1016/j.neucom.2019.12.109

Cited by 16 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is possible that the training data is not abundant enough or the structure of FCUN needs further improvement. It could be hypothesized that the performance of the deep learning method for SpecR can be further promoted by increasing the network layers and using a more efficient network structure, such as attention and transformer [38].…”

Section: Discussionmentioning

confidence: 99%

Learning a Fully Connected U-Net for Spectrum Reconstruction of Fourier Transform Imaging Spectrometers

Chen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Fourier transform imaging spectrometers (FTISs) are widely used in global hyperspectral remote sensing due to the advantages of high stability, high throughput, and high spectral resolution. Spectrum reconstruction (SpecR) is a classic problem of FTISs determining the acquired data quality and application potential. However, the state-of-the-art SpecR algorithms were restricted by the length of maximum optical path difference (MOPD) of FTISs and apodization processing, resulting in a decrease in spectral resolution; thus, the applications of FTISs were limited. In this study, a deep learning SpecR method, which directly learned an end-to-end mapping between the interference/spectrum information with limited MOPD and without apodization processing, was proposed. The mapping was represented as a fully connected U-Net (FCUN) that takes the interference fringes as the input and outputs the highly precise spectral curves. We trained the proposed FCUN model using the real spectra and simulated pulse spectra, as well as the corresponding simulated interference curves, and achieved good results. Additionally, the performance of the proposed FCUN on real interference and spectral datasets was explored. The FCUN could obtain similar spectral values compared with the state-of-the-art fast Fourier transform (FFT)-based method with only 150 and 200 points in the interferograms. The proposed method could be able to enhance the resolution of the reconstructed spectra in the case of insufficient MOPD. Moreover, the FCUN performed well in visual quality using noisy interferograms and gained nearly 70% to 80% relative improvement over FFT for the coefficient of mean relative error (MRE). All the results based on simulated and real satellite datasets showed that the reconstructed spectra of the FCUN were more consistent with the ideal spectrum compared with that of the traditional method, with higher PSNR and lower values of spectral angle (SA) and relative spectral quadratic error (RQE).

show abstract

Section: Discussionmentioning

confidence: 99%

Learning a Fully Connected U-Net for Spectrum Reconstruction of Fourier Transform Imaging Spectrometers

Chen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, this strategy does not effectively use other information from the prediction map. More recently, Li et al [26] introduced a cyclic reverse attention module into the SOD network. The cyclic reverse attention module focuses on salient areas and residual areas outside the salient areas.…”

Section: Attention-based Methodsmentioning

confidence: 99%

Cross refinement network with edge detection for salient object detection

Xiang

Ding

et al. 2021

IET Signal Processing

View full text Add to dashboard Cite

Salient object detection aims to identify the most attractive objects from images. However, their boundaries are typically of poor quality when predicted using available methods. One or multiple objects may also be left undetected if the image contains multiple objects. 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 modules and four edge‐salient cross units; and a detection network with an edge enhancement unit and a residual refinement network (RNN). For RNN training, the rough salient maps generated using the DUTS‐TR dataset are treated as a special training dataset. Compared to existing methods, the proposed network can effectively detect all objects as well as improve the boundaries of the detected objects by performing experiments on five benchmark datasets. Based on the experimental results, the proposed network outperforms existing methods both objectively and subjectively.

show abstract

“…In the aspect of residual learning, the concept of Residual Network (ResNet) was proposed by He et al [15] from Microsoft Research Institute to deal with the performance degradation problem as the number of layers grows. ResNets have outperformed common CNNs in image classification and object recognition [16][17][18]. Because of residual learning, the depth of ResNets is deeper than that of the traditional CNNs.…”

Section: Related Workmentioning

confidence: 99%

A Residual Learning-Based Network Intrusion Detection System

Man

Sun

2021

Security and Communication Networks

View full text Add to dashboard Cite

Neural networks have been proved to perform well in network intrusion detection. In order to acquire better features of network traffic, more learning layers are necessarily required. However, according to the results of the previous research, adding layers to the neural networks might fail to improve the classification results. In fact, after the number of layers has reached a certain threshold, performance of the model tends to degrade. In this paper, we propose a network intrusion detection model based on residual learning. After transforming the UNSW-NB15 data set into images, deeper convolutional neural networks with residual blocks are built to learn more critical features. Instead of the cross-entropy loss function, the modified focal loss is calculated to address the class imbalance problem in the training set and identify minor attacks in the testing set. Batch normalization and global average pooling are used to avoid overfitting and enhance the model. Experimental results show that the proposed model can improve attack detection accuracy compared with existing models.

show abstract

Recurrent reverse attention guided residual learning for saliency object detection

Cited by 16 publications

References 18 publications

Learning a Fully Connected U-Net for Spectrum Reconstruction of Fourier Transform Imaging Spectrometers

Learning a Fully Connected U-Net for Spectrum Reconstruction of Fourier Transform Imaging Spectrometers

Cross refinement network with edge detection for salient object detection

A Residual Learning-Based Network Intrusion Detection System

Contact Info

Product

Resources

About