Daniel Lima-López
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Daniel Lima-López has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Francisco David Camacho-Gonzalez
Instituto Nacional de Astrofísica, Óptica y Electrónica, Puebla 72840, Mexico
1 shared publication - Leopoldo Altamirano-Robles
Instituto Nacional de Astrofísica, Optica y Electrönica
1 shared publication - Pilar Gomez-Gil
National Institute of Astrophysics, Optics and Electronics
1 shared publication - Saúl Zapotecas-Martínez
Instituto Nacional de Astrofísica Óptica y Electrónica, Sta. María Tonantzintla, Puebla 72840, Mexico
1 shared publication
Latest Publications
- 4 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (3) , 239-248
On the building of efficient Fourier Convolutional Neural Networks
In computer vision tasks, Convolutional Neural Networks (CNN) have been the cornerstone to implement numerous models with outstanding results. Nevertheless, its high computational cost hinders its full potential when working with low-end devices. To overcome this drawback, various models have been proposed to take advantage of the properties of the convolution theorem to reduce calculations in CNN architectures. However, the use of the Fourier domain incurs in an increment of the number of weights of the kernels because they are defined using complex variable. In this work, we present a strategy to reduce such numbers by defining a reduced representation, which considers a limited amount of components to keep the parameter count comparable to that of a standard CNN. In deed, we introduce a novel layer, called Linear Transform, that learns to identify the most essential components of a frequency representation, building an appropriate reduced representation. Our experiments on image classification using databases MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 showed that our proposal contains fewer parameters and floating point operations, in comparison with both conventional and Fourier CNN architectures. Moreover, the Linear Transform layer produced an improvement in the accuracy in several cases. Cases where accuracy decreases are also analyzed.
- 4 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (3) , 239-248
On the building of efficient Fourier Convolutional Neural Networks
In computer vision tasks, Convolutional Neural Networks (CNN) have been the cornerstone to implement numerous models with outstanding results. Nevertheless, its high computational cost hinders its full potential when working with low-end devices. To overcome this drawback, various models have been proposed to take advantage of the properties of the convolution theorem to reduce calculations in CNN architectures. However, the use of the Fourier domain incurs in an increment of the number of weights of the kernels because they are defined using complex variable. In this work, we present a strategy to reduce such numbers by defining a reduced representation, which considers a limited amount of components to keep the parameter count comparable to that of a standard CNN. In deed, we introduce a novel layer, called Linear Transform, that learns to identify the most essential components of a frequency representation, building an appropriate reduced representation. Our experiments on image classification using databases MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 showed that our proposal contains fewer parameters and floating point operations, in comparison with both conventional and Fourier CNN architectures. Moreover, the Linear Transform layer produced an improvement in the accuracy in several cases. Cases where accuracy decreases are also analyzed.
- 11 October 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 261
Vector quantization-driven image compression through multi-objective evolutionary algorithms
- 11 October 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 261
Vector quantization-driven image compression through multi-objective evolutionary algorithms