Rain-Density Squeeze-and-Excitation Residual Network for Single Image Rain-removal

Hu, Xipu; Wang, Wenhao; Pang, Cheng; Lan, Rushi; Luo, Xiangfeng

doi:10.1109/icaci.2019.8778583

Cited by 5 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, the feature extraction process is also disturbed by the randomness of the main object locations and redundant background regions. Traditional CNNs tend to focus on global semantics [14], and this secondary or irrelevant information can easily interfere with their ability to extract features belonging to the main object, thereby affecting the final performance of these models.…”

Section: Weaknesses Regarding the Main Semantic Featuresmentioning

confidence: 99%

“…Suppose that we have an identity map; then, H (X i ) = X i . An attention mechanism can quickly focus on the main information of an image and extract key features while suppressing the formation of redundant information [14]. To improve the ability of a CNN model to adaptively extract key features and increase the diversity of discriminative features, Hu et al [58] proposed a channel-based attention mechanism called squeeze-and-excitation (SE).…”

Section: Figurementioning

confidence: 99%

“…An attention mechanism is an algorithm that can quickly and accurately focus on the target object while suppressing irrelevant information. It perfectly simulates the way in which humans understand and observe images [14]. In recent years, many different attention mechanisms have been produced and applied to various fields, such as natural language processing, object detection and image recognition.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A lightweight and stochastic depth residual attention network for remote sensing scene classification

Wang

Yuan

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Due to the rapid development of satellite technology, high‐spatial‐resolution remote sensing (HRRS) images have highly complex spatial distributions and multiscale features, making the classification of such images a challenging task. The key to scene classification is to accurately understand the main semantic information contained in images. Convolutional neural networks (CNNs) have outstanding advantages in this field. Deep CNNs (D‐CNNs) with better performance tend to have more parameters and higher complexity. However, shallow CNNs have difficulty extracting the key features of complex remote sensing images. In this paper, we propose a lightweight network with a random depth strategy for remote sensing scene classification (LRSCM). We construct a convolutional feature extraction module, DCAB, which incorporates depthwise separable convolutional and inverted residual structures, effectively reducing the numbers of required parameters and computations, and retains and utilizes low‐level features. In addition, coordinate attention (CA) is integrated into the module, thereby further improving the network's ability to extract key local information. To further reduce the complexity of model training, the residual module adopts a stochastic depth strategy, providing the network with a random depth. Comparative experiments on five public datasets show that the LRSCM network can achieve results comparable to those of other state‐of‐the‐art methods.

show abstract

Section: Weaknesses Regarding the Main Semantic Featuresmentioning

confidence: 99%

Section: Figurementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A lightweight and stochastic depth residual attention network for remote sensing scene classification

Wang

Yuan

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…In this technique, instead of identity mapping as residual, the residual squeezing is used as an additional useful information for basic squeeze operation [27]. The CMPE-SE squeezes both residual and input feature maps, concatenates the output squeezed signals, excites the concatenated signal and re-calibrate the channels of input feature map accordingly [34]. This work presented four different versions with their comparisons.…”

Section: Competitive Inner-imaging Squeeze and Excitation For Residua...mentioning

confidence: 99%

Localized Squeeze and Excitation Block

Shaukat,

Farid

2023

Preprint

View full text Add to dashboard Cite

In this article a new technique called Localized Squeeze and Excitation (LSE) Block is proposed. Using proposed LSE-block one can extract core features from the images in the early stage, which results in smaller deep neural network with much less number of parameters; results in less computation time. By using our proposed technique one can reduce the size of any large deep neural network model. For experimentation the model named ResNet-50 is selected and it is shown that how ResNet-50 can be converted into a smaller neural network by using our proposed technique with better accuracy and less processing time. This work is evaluated on the Breast Cancer Histopathological Image Dataset, both for binary and multi-class problems.

show abstract

“…DL-based methods have achieved remarkable results in single image rain streaks removal [16][17][18][19]. Hu et al [16] proposed the rain-density squeeze-and-excitation residual network (RDSER-NET) to remove rain streaks from a single image.…”

Section: Introductionmentioning

confidence: 99%

GSDerainNet: A Deep Network Architecture Based on a Gaussian Shannon Filter for Single Image Deraining

Yao,

Shi,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the continuous advancement of target detection technology in remote sensing, target detection technology in images captured by drones has performed well. However, object detection in drone imagery is still a challenge under rainy conditions. Rain is a common severe weather condition, and rain streaks often degrade the image quality of sensors. The main issue of rain streaks removal from a single image is to prevent over smoothing (or underclearing) phenomena. Aiming at the above problems, this paper proposes a deep learning (DL)-based rain streaks removal framework called GSDerainNet, which properly formulates the single image rain streaks removal problem; rain streaks removal is aptly described as a Gaussian Shannon (GS) filter-based image decomposition problem. The GS filter is a novel filter proposed by us, which consists of a parameterized Gaussian function and a scaled Shannon function. Two-dimensional GS filters exhibit high stability and effectiveness in dividing an image into low- and high-frequency parts. In our framework, an input image is first decomposed into a low-frequency part and a high-frequency part by using the GS filter. Rain streaks are located in the high-frequency part. We extract and separate the rain features of the high-frequency part through a deep convolutional neural network (CNN). The experimental results obtained on synthetic data and real data show that the proposed method can better suppress the morphological artifacts caused by filtering. Compared with state-of-the-art single image rain streaks removal methods, the proposed method retains finer image object structures while removing rain streaks.

show abstract

Rain-Density Squeeze-and-Excitation Residual Network for Single Image Rain-removal

Cited by 5 publications

References 34 publications

A lightweight and stochastic depth residual attention network for remote sensing scene classification

A lightweight and stochastic depth residual attention network for remote sensing scene classification

Localized Squeeze and Excitation Block

GSDerainNet: A Deep Network Architecture Based on a Gaussian Shannon Filter for Single Image Deraining

Contact Info

Product

Resources

About