Reconstruction of Generative Adversarial Networks in Cross Modal Image Generation with Canonical Polyadic Decomposition

Ma, Ruixin; Lou, Junying; Gao, Jing

doi:10.1155/2021/8868781

Cited by 8 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The batch size was set to 16 and the model was trained for 200 epochs. MultiStepLR is a learning rate decay method used in PyTorch [86] that adjusts the learning rate at set intervals [87]. The initial learning rate was set to 0.01.…”

Section: Training Methodsmentioning

confidence: 99%

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

Tang,

Zhao,

Zhang

et al. 2024

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

View full text Add to dashboard Cite

Abstract-Poverty is a global challenge, the effects of which are felt on the individual to national scale. To develop effective support policies to reduce poverty, local governments require precise poverty distribution data, which are lacking for many areas. In this study, we proposed a model to estimate poverty on a spatial scale of 10 × 10 km by combining features extracted from multiple data sources, including nighttime light remote sensing data, normalized difference vegetation index, surface reflectance, land cover type, and slope data, and applied the model to Nigeria. Considering that the trends of environmental factors contain valid information related to poverty, time-series features were extracted through convolutional long short-term memory and used for the assessment. The poverty level is represented by the wealth index derived from the Demographic and Health Survey Program. The model exhibited a good ability to estimate poverty, with an R 2 of 0.73 between the actual and estimated wealth index in Nigeria in 2018. Applying the proposed model to poverty estimation for Nigeria in 2021 yielded an R 2 value of 0.69, indicating good generalization ability. To further validate model reliability, we compared the assessment results with high-resolution satellite imagery and a state-level multidimensional poverty index. We also investigated the impact of incorporating time-series features on the accuracy of poverty assessment. Results showed that the addition of time-series features increased the accuracy of poverty estimation from 0.64 to 0.73. The proposed method has valuable applications for estimating poverty at the grid scale in countries without such data.

show abstract

Section: Training Methodsmentioning

confidence: 99%

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

Tang,

Zhao,

Zhang

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…To decompose the input matrices, different methods exist, such as Singular Value Decomposition (SVD) [20][21][22], QR decomposition [23,24], interpolative decomposition [25], and none-negative factorization [26]. Given that tensors are multidimensional generalizations of matrices, they need different methods to be decomposed e.g., Tucker Decomposition [27,28], Canonical Polyadic Decomposition (CPD) [29,30], and Tensor Train (TT) Decomposition [31]. Another way to decompose tensors is to transform the input tensor into a twodimensional (2D) matrix and then perform the decomposition process using one of the above mentioned matrix decomposition techniques [32,33].…”

Section: Low-rank Factorizationmentioning

confidence: 99%

A Practical Approach for Employing Tensor Train Decomposition in Edge Devices

Kokhazadeh

Κεραμίδας

Kelefouras

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep Neural Networks (DNN) have made significant advances in various fields including speech recognition and image processing. Typically, modern DNNs are both compute and memory intensive, therefore their deployment in low-end devices is a challenging task. A well-known technique to address this problem is Low-Rank Factorization (LRF), where a weight tensor is approximated by one or more lower-rank tensors, reducing both the memory size and the number of executed tensor operations. However, the employment of LRF is a multi-parametric optimization process involving a huge design space where different design points represent different solutions trading-off the number of FLOPs, the memory size, and the prediction accuracy of the DNN models. As a result, extracting an efficient solution is a complex and time-consuming process. In this work a new methodology is presented that formulates the LRF problem as a (FLOPs vs. memory vs. prediction accuracy) Design Space Exploration (DSE) problem. Then, the DSE space is drastically pruned by removing inefficient solutions. Our experimental results prove that the design space can be efficiently pruned, therefore extract only a limited set of solutions with improved accuracy, memory, and FLOPs compared to the original (non-factorized) model. Our methodology has been developed as a stand-alone, parameterized module integrated into T3F library of TensorFlow 2.X.

show abstract

“…Synthetic Datasets Goodfellow et al ( 2014) proposed GAN as a new generative modeling framework [14] to synthesize new data with the same characteristics from training examples, visually approximating the training data set. Various GANbased methods have been proposed for image synthesis in recent years [15], [16], [17], [18], [19], [20], [21], [22], [23], and [24] with applications spreading rapidly from computer vision and machine learning communities to domain-specific areas such as medical [25] [26], [27], [28], [29], and remote sensing [30], [31], [32] [33], [34], [35], [36], [37], [38], [39], [40], and [41]; industrial process [42], [43], [44], [45], [46], [47], and [48]; and agriculture [49], [50], [51], [52].…”

Section: B Gan (Generative Adversarial Network) To Producementioning

confidence: 99%

Oil Palm USB (Unstripped Bunch) Detector Trained on Synthetic Images Generated by PGGAN

Aji,

Bin Ghazali,

Akbar

2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Identifying Unstriped Bunches (USB) is a pivotal challenge in palm oil production, contributing to reduced mill efficiency. Existing manual detection methods are proven time-consuming and prone to inaccuracies. Therefore, we propose an innovative solution harnessing computer vision technology. Specifically, we leverage the Faster R-CNN (Region-based Convolution Neural Network), a robust object detection algorithm, and complement it with Progressive Growing Generative Adversarial Networks (PGGAN) for synthetic image generation. Nevertheless, a scarcity of authentic USB images may hinder the application of Faster R-CNN. Herein, PGGAN is assumed to be pivotal in generating synthetic images of Empty Fruit Bunches (EFB) and USB. Our approach pairs synthetic images with authentic ones to train the Faster R-CNN. The VGG16 feature generator serves as the architectural backbone, fostering enhanced learning. According to our experimental results, USB detectors that were trained solely with authentic images resulted in an accuracy of 77.1%, which highlights the potential of this methodology. However, employing solely synthetic images leads to a slightly reduced accuracy of 75.3%. Strikingly, the fusion of authentic and synthetic images in a balanced ratio of 1:1 fuels a remarkable accuracy surge to 87.9%, signifying a 10.1% improvement. This innovative amalgamation underscores the potential of synthetic data augmentation in refining detection systems. By amalgamating authentic and synthetic data, we unlock a novel dimension of accuracy in USB detection, which was previously unattainable. This contribution holds significant implications for the industry, ensuring further exploration into advanced data synthesis techniques and refining detection models.

show abstract

Reconstruction of Generative Adversarial Networks in Cross Modal Image Generation with Canonical Polyadic Decomposition

Cited by 8 publications

References 22 publications

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

Poverty Estimation Using a ConvLSTM-Based Model With Multisource Remote Sensing Data: A Case Study in Nigeria

A Practical Approach for Employing Tensor Train Decomposition in Edge Devices

Oil Palm USB (Unstripped Bunch) Detector Trained on Synthetic Images Generated by PGGAN

Contact Info

Product

Resources

About