Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification

Hou, Wei; Chen, Na; Peng, Jiangtao; Sun, Weiwei; Du, Qian

doi:10.1109/jstars.2023.3237566

Cited by 7 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Self-paced learning is a form of joint learning that exerts control over the training process by gradually incorporating increasingly complex samples, starting from the simplest ones [33]. Self-paced learning is useful in various types of computer vision and pattern recognition tasks, including longterm tracking [34],natural language processing [35], image classification [36]. A theoretical study proved that self-paced learning is robust to noisy samples and can address local optimum problem [37].…”

Section: B Self-paced Learningmentioning

confidence: 99%

Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Wen,

Huang,

Yang

et al. 2024

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

View full text Add to dashboard Cite

In recent years, numerous change detection methodologies have been proposed, with a predominant focus on binary change detection. Furthermore, there exists a paucity of research addressing semantic change detection in scenarios where solely binary change labels are available. This article introduces a multi-task network for semantic change detection. First, 3D ResUnet model is employed to generate initial multitemporal land cover results through post classification comparison (PCC). Subsequently, the multi-task network, encompassing two sub-tasks-binary change detection and multi-temporal semantic segmentation-is proposed. Specifically, the shared branch of the network employs 3D residual blocks to extract joint spectral-spatial features. In the subsequent taskspecific branch, a 3D GAN is incorporated for the binary change detection task to enhance the discrimination ability of latent high-level features for changes. Novel adaptive self-paced learning and certainty-weighted focal loss are proposed for multitemporal semantic segmentation to mitigate adverse effects from noisy semantic labels by considering sample complexity and reliability in the network optimization process. Experiments conducted on the Orbita Hyperspectral Dataset in the Xiong'an New Area demonstrate the superior performance of the proposed method, achieving 99.28% and 76.60% for Overall Accuracy (OA) and Kappa, respectively. This outperformance is notable when compared to other methods, such as Str4 and Bi-SRNet, showing an increase of 39.82% and 54.17% for Kappa. Moreover, comparative experiments on SECOND further confirm the advantage of the proposed method, achieving 54.62% for Kappa and outperforming other comparative methos like Bi-SRNet

show abstract

Section: B Self-paced Learningmentioning

confidence: 99%

Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Wen,

Huang,

Yang

et al. 2024

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

View full text Add to dashboard Cite

show abstract

Enhanced channel prediction in large‐scale5G MIMO‐OFDMsystems using pyramidal dilation attention convolutional neural network

Rathish,

Manojkumar,

Thanga Mariappan

et al. 2024

Internet Technology Letters

View full text Add to dashboard Cite

In order to enhance communication while minimizing complexity in 5G and beyond, MIMO‐OFDM systems need accurate channel prediction. In order to enhance channel prediction, decrease Error Vector Magnitude, Peak Power, and Adjacent Channel Leakage Ratio, this study employs the Pyramidal Dilation Attention Convolutional Neural Network (PDACNN). Simplified clipping with filtering (SCF) reduces PAPR data, and this technique employs a PDACNN trained with the reduced data. By combining attention techniques with pyramidal dilated convolutions, the suggested PDACNN architecture is able to extract OFDM channel parameters across several scales. Attention approaches enhance channel prediction by allowing the model to dynamically concentrate on essential information. The primary objective is to make use of the network's ability to comprehend intricate spatial–temporal connections in OFDM channel data. The goal of these techniques is to make channel forecasts more accurate and resilient while decreasing concerns about EVM, Peak Power, and ACLR. To confirm the effectiveness of the suggested CP‐LSMIMO‐OFDM‐PDACNN, we measure its spectral efficiency, peak‐to‐average power ratio, bit error rate (BER), signal‐to‐noise ratio (SNR), and throughput. Throughput gains of 23.76%, 30.45%, and 18.97% are achieved via CP‐LSMIMO‐OFDM‐PDACNN, while bit error rates of 20.67%, 12.78%, and 19.56% are reduced. PAPRs of 21.66%, 23.09%, and 25.11% are also decreased.

show abstract

Detecting fault in photovoltaic system with a hybrid PDACNN-IDMOA methodology

Rashmi,

Manjusha,

Anish John Paul

et al. 2024

Electr Eng

View full text Add to dashboard Cite

Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification

Cited by 7 publications

References 51 publications

Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Enhanced channel prediction in large‐scale5G MIMO‐OFDMsystems using pyramidal dilation attention convolutional neural network

Detecting fault in photovoltaic system with a hybrid PDACNN-IDMOA methodology

Contact Info

Product

Resources

About