Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

EMViT-DDPM: An Equilibrium-Based ViT Diffusion Framework for Data Augmentation in Multispectral Land Cover Classification

  • Barreiro Domínguez, Víctor Xesús
  • Blanco Heras, Dora
  • Argüello Pedreira, Francisco
The scarcity and imbalance of labeled samples, common in remote sensing datasets, pose significant challenges for accurate analysis and classification, often leading to substantial bias against minority classes. To address these issues, we propose EMViT-DDPM, an equilibrium-based data augmentation framework leveraging vision transformer (ViT)-based denoising diffusion probabilistic models (DDPMs). Unlike generative adversarial network (GAN)-based augmentation techniques commonly found in the literature, our framework is not tied to any specific classifier. It leverages a ViT architecture enhanced with the AdaLN block, which is designed to minimize computational costs while effectively capturing data complexity. By adopting diffusion models (DDPMs), the framework achieves greater training robustness, improved generalization, and better quality control over generated samples compared to GANs. To address class imbalance, we introduce equilibrium-based data augmentation (), which assigns different augmentation proportions to each class based on their respective sizes. In addition, a superpixel-based segmentation preprocessing step is proposed for patch generation, tailoring the data augmentation method specifically to high-spatial-resolution multispectral remote sensing imagery. Finally, we propose a novel strategy for the evaluation of data-augmentation quality, based on a new judge model trained over balanced classes. This allows a more precise evaluation of Fréchet inception distance, precision (fidelity), and recall (diversity)
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

Efficient Semantic Segmentation of Multispectral Land Cover Images Using Mask2Former

  • Canosa García, Pablo
  • Ordóñez Iglesias, Álvaro
  • Blanco Heras, Dora
  • Argüello Pedreira, Francisco
Semantic segmentation for EO is a process that involves assigning a specific label or category to each pixel in an image, enabling precise analysis for land cover applications such as environmental conservation, urban planning or disaster management. Deep learning-based segmentation models have proliferated in recent years, but they often are not well adapted to the unique properties of multi and hyperspectral images, frequently used in remote sensing. Mask2Former is a universal segmentation model based on the concept of masked attention and employs a pretrained classification model as backbone to create intermediate representations. This article presents a preliminary adaptation of Mask2Former for the segmentation of multispectral remote sensing images. This adaptation includes modifying the backbone to accept multispectral inputs and adapting the data processing pipelines to leverage all available spectral bands effectively. The computational cost of the method has also been analyzed as an initial assessment of potential scalability and efficiency for large-scale applications. Experimental results using the FiveBillionPixels dataset reveal a notable improvement in segmentation accuracy when incorporating multispectral bands, outperforming RGB-only performance without a relevant increase in computational cost.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

A hybrid CUDA, OpenMP, and MPI parallel TCA-based domain adaptation for classification of very high-resolution remote sensing images

  • Suárez Garea, Jorge Alberto
  • Blanco Heras, Dora
  • Argüello Pedreira, Francisco
  • Demir, Begüm
Domain Adaptation (DA) is a technique that aims at extracting information from a labeled remote sensing image to allow classifying a different image obtained by the same sensor but at a different geographical location. This is a very complex problem from the computational point of view, specially due to the very high-resolution of multispectral images. TCANet is a deep learning neural network for DA classification problems that has been proven as very accurate for solving them. TCANet consists of several stages based on the application of convolutional filters obtained through Transfer Component Analysis (TCA) computed over the input images. It does not require backpropagation training, in contrast to the usual CNN-based networks, as the convolutional filters are directly computed based on the TCA transform applied over the training samples. In this paper, a hybrid parallel TCA-based domain adaptation technique for solving the classification of very high-resolution multispectral images is presented. It is designed for efficient execution on a multi-node computer by using Message Passing Interface (MPI), exploiting the available Graphical Processing Units (GPUs), and making efficient use of each multicore node by using Open Multi-Processing (OpenMP). As a result, an accurate DA technique from the point of view of classification and with high speedup values over the sequential version is obtained, increasing the applicability of the technique to real problems
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application

  • Castro, Manuel de
  • Osorio, Roberto
  • Andújar, Francisco J.
  • Carratalá-Sáez, Rocío
  • Torres, Yuri
  • Llanos, Diego R.
[Abstract]: With the growing popularity of FPGA-based accelerators in HPC applications, new challenges have emerged, particularly in terms of programming and portability. This paper provides an overview of the current state of FPGA tools and their limitations. This study evaluates the performance and portability of two frameworks, SYCL and OpenCL, for developing HPC FPGA solutions. The case of porting a highly-parallel application to FPGAs is studied. First, naïve, low-development-effort implementations are presented using both ND-range and single-task types of kernels, and their performance is evaluated. Subsequently, an optimized FPGA-centric approach is presented and assessed using metrics from the compilation framework. Finally, the different approaches presented are implemented using OpenCL and SYCL and their performance is evaluated. Results reveal that ND-range kernels offer high portability for highly parallel applications, while single-task codes exhibit significantly lower portability. Additionally, SYCL struggles to generate efficient hardware architectures for this kind of application when described as single-task codes, although its performance when following the ND-range approach is surprisingly high., This work was supported in part by Spanish Ministerio de Ciencia e Innovación and the European Regional Development Fund (ERDF) Program of the European Union, (NATASHA Project), under Grant PID2022-142292NB-I00; in part by Junta de Castilla y León-FEDER Grants, (PROPHET-2 Project), Junta de Castilla y León, Spain under Grant VA226P20; in part by MCIN/AEI/10.13039/ 501100011033 through European Union NextGenerationEU/PRTR, under Grant TED2021 130367B I00; and in part by MCIN/AEI/10.13039/501100011033 through ERDF a way of making Europe, EU, under Grant PID2022-136435NB-I00. The work of Manuel De Castro was supported by Spanish Ministerio de Ciencia, Innovación y Universidades, through Ayudas para la Formación de Profesorado Universitario FPU 2022., Junta de Castilla y León; VA226P20
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Implementation of a motion estimation algorithm for Intel FPGAs using OpenCL

  • Castro, Manuel de
  • Osorio, Roberto
  • López Vilariño, David
  • González-Escribano, Arturo
  • Llanos, Diego R.
Financiado para publicación en acceso aberto: CRUE-CSIC, [Abstract]: Motion Estimation is one of the main tasks behind any video encoder. It is a computationally costly task; therefore, it is usually delegated to specific or reconfigurable hardware, such as FPGAs. Over the years, multiple FPGA implementations have been developed, mainly using hardware description languages such as Verilog or VHDL. Since programming using hardware description languages is a complex task, it is desirable to use higher-level languages to develop FPGA applications.The aim of this work is to evaluate OpenCL, in terms of expressiveness, as a tool for developing this kind of FPGA applications. To do so, we present and evaluate a parallel implementation of the Block Matching Motion Estimation process using OpenCL for Intel FPGAs, usable and tested on an Intel Stratix 10 FPGA. The implementation efficiently processes Full HD frames completely inside the FPGA. In this work, we show the resource utilization when synthesizing the code on an Intel Stratix 10 FPGA, as well as a performance comparison with multiple CPU implementations with varying levels of optimization and vectorization capabilities. We also compare the proposed OpenCL implementation, in terms of resource utilization and performance, with estimations obtained from an equivalent VHDL implementation., Junta de Castilla y León; VA226P20, Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C 2021/30, This work has been funded by the Consejería de Educación of Junta de Castilla y León, Project PROPHET-2 (VA226P20), and Ministerio de Economía, Industria y Competitividad of Spain, European Regional Development Fund (ERDF) program: Project PCAS (TIN2017-88614-R). David L. Vilariño is funded by Ministerio de Economía, Industria y Competitividad of Spain (PID2019-104834 GB-I00). Roberto R. Osorio is funded by the Ministry of Science and Innovation of Spain (PID2019-104184RB-I00 / AEI / 10.13039/501100011033), and by Xunta de Galicia and FEDER funds of the EU (Centro de Investigacion de Galicia accreditation 2019-2022, ref. ED431G 2019/01; Consolidation Program of Competitive Reference Groups, ref. ED431C 2021/30). This work was also supported in part by grant TED2021-130367B-I00 funded by MCIN/AEI/10.13039/501100011033 and by “European Union NextGenerationEU/PRTR”.