NLRNet: An Efficient Nonlocal Attention ResNet for Pansharpening

Lei, Dajiang; Chen, Hao; Zhang, Liping; Li, Weisheng

doi:10.1109/tgrs.2021.3067097

Cited by 31 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, deep learning has shown a great ability for feature presentation and nonlinear mapping. Specifically, CNNs extract features from the original images and perform nonlinear mapping by activation functions [1]. Trained on a dataset, CNNs learn the generality of the data and then are applied to the data they have not seen.…”

Section: A Convolutional Neural Network Based Methodsmentioning

confidence: 99%

“…ESPITE the rapid development of remote sensing technology, the quality of remote sensing images is still influenced by some factors, such as engineering roadblocks and cost, thus leading to the problem of achieving high spatial and spectral resolutions simultaneously [1]. The tradeoff between spatial and spectral resolution is required.…”

Section: Introductionmentioning

confidence: 99%

“…For example, a VO-based approach [21] constructed an energy functional and converted pansharpening into an optimization problem, while [22,23] solved the pansharpening problem within a Bayesian estimation framework. Usually, CS-based and MRA-based methods are more efficient than VO-based and Bayesian methods, but the quality of pansharpened images is not satisfactory enough compared with the latter [1,11]. In general, the fusion of spectral and spatial information is a complex nonlinear problem, and the assumption of a linear model may limit the accuracy of the fusion results.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, convolutional neural networks (CNNs) have achieved great success in the field of computer vision. They have also been introduced in pansharpening task and have proven to be effective [1,24,25]. Since superresolution is also an inverse problem to enhance the resolution of images, architectures proposed for superresolution have been used to address the pansharpening task.…”

Section: Introductionmentioning

confidence: 99%

“…And more details will be discussed in section IV. Furthermore, we adopt the residual architecture used in [1,27,28] to improve the accuracy of pansharpened results, so that the CNN only needs to generate the residual component. In the residual branch, we use nearest neighbor interpolation to upsample the MS image which avoids the introduction of unknown pixels but brings in mosaics.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Pansharpening via Subpixel Convolutional Residual Network

Zheng

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this paper, we propose a new pansharpening architecture called Sub-Pixel Convolutional Residual Network to obtain high-resolution multispectral (MS) images. Different from previous works, we extract features from MS images in a lowresolution space and pays more attention to the balance of spectral and spatial information. Our architecture consists of two branches: the feature extraction branch and the residual branch. The former adopts a four-layer convolutional network to extract features, and then upsamples the feature maps using a subpixel convolution layer. For the latter, we combine nearest neighbor interpolation and guided filter to yield a preliminary image with fundamental spectral and spatial information. With the outputs of the two branches, we can merge them and yield a pansharpened image. The proposed method was compared with several representative methods. The experimental results demonstrate that our method achieves a high fusion accuracy while maintaining a good balance between the spectral and the spatial resolution.

show abstract

Section: A Convolutional Neural Network Based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Pansharpening via Subpixel Convolutional Residual Network

Zheng

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

A Comprehensive Overview of Satellite Image Fusion: From Classical Model-Based to Cutting-Edge Deep Learning Approaches

Pereira-Sánchez,

Sans,

Navarro

et al. 2024

Unsupervised and Semi-Supervised Learning

View full text Add to dashboard Cite

RETRACTED ARTICLE: Sustainable strategy for online physical education teaching using ResNet34 and big data

Liu

2023

Soft Comput

View full text Add to dashboard Cite

Since the global COVID-19 outbreak in the spring of 2020, online instruction has replaced traditional classroom instruction as the main method of educating students. Teaching physical education online can be challenging, as it may be difficult to teach students certain movements, accurate student mobility, and appropriate exercise assignments. This paper proposed an online teaching support system with sustainable development features that utilize several large data sets. The system is based on the deep learning image recognition algorithm ResNet34, which can analyze and correct student actions in real-time for gymnastics, dance, basketball, and other sports. By combining the attention mechanism module with the original ResNet34, the detection precision of the system can be enhanced. The sustainability of the system is evident from the fact that the data set can be expanded in response to the emergence of new sports categories and can be kept current in real-time. According to experiments, the target identification accuracy of the proposed system, which combines ResNet34 and the attention mechanism, is higher than that of several other methods currently in use. The proposed techniques outperform the original ResNet34 in terms of accuracy, precision, and recall by 4.1%, 2.8%, and 3.6%, respectively. The suggested approach significantly improves student action correction in virtual sports instruction.

show abstract

NLRNet: An Efficient Nonlocal Attention ResNet for Pansharpening

Cited by 31 publications

References 44 publications

Pansharpening via Subpixel Convolutional Residual Network

Pansharpening via Subpixel Convolutional Residual Network

A Comprehensive Overview of Satellite Image Fusion: From Classical Model-Based to Cutting-Edge Deep Learning Approaches

RETRACTED ARTICLE: Sustainable strategy for online physical education teaching using ResNet34 and big data

Contact Info

Product

Resources

About