3-D Gravity Intelligent Inversion by U-Net Network With Data Augmentation

Zhou, Xinyi; Chen, Zhaoxi; Lv, Yandong; Wang, Shuai

doi:10.1109/tgrs.2023.3241310

Cited by 9 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In recent years, deep convolutional neural networks (DCNNs) 19 – 23 have demonstrated state-of-the-art and sometimes even human-level performance in solving many computer vision problems, such as image classification, 24 , 25 object detection, 26 , 27 image segmentation, 28 , 29 etc. For line detection, 30 – 33 DCNN-based methods have also been proposed for tasks such as edge detection, contour detection, boundary segmentation, etc.…”

Section: Introductionmentioning

confidence: 99%

FSDGNet: frequency and spatial dual guide network for crack detection

Liu,

Yuan,

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Cracks are one of the major threats to the safe operation of civil infrastructures, so timely and accurate detection of cracks is crucial for accident prevention. However, in practical applications, the poor continuity and low contrast of many cracks (e.g., pavement cracks) pose a great challenge to image-based crack detection. In previous approaches, the detection results are often unsatisfactory due to the limitation of the dataset and the singularity of the detection method. To solve this problem, we propose a frequency and spatial dual guide network for crack detection. First, global frequency domain information is processed by the fast Fourier transform to extract low-level features, and then the convolutional neural network uses global frequency domain information to learn local features of the image to extract highlevel features. Finally, the feature maps of the two are weighted and fused element by element to obtain the final detection result. Extensive experiments show that our method is superior to any other existing method.

show abstract

Section: Introductionmentioning

confidence: 99%

FSDGNet: frequency and spatial dual guide network for crack detection

Liu,

Yuan,

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…These include regularization techniques 14 , such as L1 and L2 regularization, as well as dropout 15 , which aim to prevent overfitting 11 . Furthermore, data augmentation techniques 16 have been utilized to diversify the training dataset, mitigating the risk of overfitting. Additionally, strategies like weight initialization 17 have been employed to facilitate gradient stability and prevent issues like vanishing or exploding gradients.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Correlation Branch Network for Image Classification

Li,

Luo,

Zhu

2023

Preprint

View full text Add to dashboard Cite

ResNets are currently the mainstream networks used in engineering and research. However, cellular neural networks have inherent flaws, including typical problems such as structural defects and loss of convolutional information. In view of this, we propose a multi-branch deep network based on the correlation features of feature maps. Convolution-correlated features are derived from covariance matrices of feature maps within network layers. Because the covariance matrix belongs to a Riemannian manifold, in the network branch we use a self-attention network to map it to a linear space and combine it with advanced deep features to achieve image recognition. Using the covariance information of feature maps enables the network to effectively compensate for important information that may be lost in ResNet, and the multi-branch structure of the network effectively solves the problem of gradient disappearance or explosion during deep network training.The experimental results of image classification on four data sets: Cifar-10, Cifar-100,Flower-102 and Car-196 show that our proposed network significantly improves the performance of existing networks. It is worth noting that the multi-branch network model based on cooperative prevention difference we proposed can also be extended to the Transformer network, so it has good application prospects.

show abstract

“…이 분석에 연구도 소개되었다. Kim and Byun, 2020;Feng et al, 2021;Yang et al, 2022;Zhao et al, 2022;Zhou et al, 2023). 또 한, 비지도학습, 준지도학습, 전이학습과 같은 접근법으로 자료 부족 문제를 해결하기 위한 연구들도 수행되고 있고 (e.g., Alfarraj and AlRegib, 2019;Di et al, 2020;Liu et al, 2021a;Song et al, 2022) 료 간의 상호작용을 직접적으로 모델링하는 데 제한이 있 어 성능 저하의 가능성이 있다.…”

unclassified

Deep Learning in Geophysics: Current Status, Challenges, and Future Directions

Yu,

Oh,

Kong

et al. 2024

J. Korean Soc. Miner. Energy Resour. Eng.

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technology, machine learning and deep learning techniques have been actively applied in the field of exploration geophysics. In this study, we extensively investigated the application of deep learning in geophysical techniques including seismic, gravity, magnetic, electromagnetics, ground penetrating radar, and joint inversion. Recent research has confirmed that deep learning techniques optimized for geophysical problems are being developed that transcend traditional theory-based approaches, suggesting that deep learning is becoming a new paradigm in the field of geophysics. Despite these technological advances, there are still challenges to be overcome, such as a lack of training data, model opacity, and heterogeneity between training data and field data, and this study suggests future research directions to address these aspects.

show abstract

3-D Gravity Intelligent Inversion by U-Net Network With Data Augmentation

Cited by 9 publications

References 53 publications

FSDGNet: frequency and spatial dual guide network for crack detection

FSDGNet: frequency and spatial dual guide network for crack detection

Convolutional Correlation Branch Network for Image Classification

Deep Learning in Geophysics: Current Status, Challenges, and Future Directions

Contact Info

Product

Resources

About