Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Silva DA"'
Autor:
Jose Douglas Bratti, Paulo Drews, Eglen Protas, Silvia Silva da Costa Botelho, Joel Felipe de Oliveira Gaya
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 30:2231-2243
Convolutional neural networks (CNNs) are powerful machine learning models that have become the state of the art in several problems in the areas of computer vision and image processing. Nevertheless, the knowledge of why and how these models present
Autor:
Paulo L. J. Drews-Jr, Lucas Ricardo Vieira Messias, Silvia Silva da Costa Botelho, Cristiano Rafael Steffens
Publikováno v:
Intelligent Systems ISBN: 9783030613761
BRACIS
BRACIS
Image classification is a well-established problem in computer vision. Most state-of-the-art models rely on Convolutional Neural Networks to achieve near-human performance in that task. However, CNNs have shown to be susceptible to image manipulation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2afd1939ff3e18d2d4966249141813d6
https://doi.org/10.1007/978-3-030-61377-8_15
https://doi.org/10.1007/978-3-030-61377-8_15
Autor:
Lucas Ricardo Vieira Messias, Paulo Drews, Silvia Silva da Costa Botelho, Cristiano Rafael Steffens
Publikováno v:
2019 Latin American Robotics Symposium (LARS), 2019 Brazilian Symposium on Robotics (SBR) and 2019 Workshop on Robotics in Education (WRE).
Convolutional Neural Networks stand the current state-of-the-art in image recognition, as well as many computer vision tasks. Nevertheless, these architectures have been shown to be vulnerable to image manipulations, which may undermine the reliabili
Publikováno v:
BRACIS
Advances in remote sensing and machine learning technologies allow a better understanding of satellite images and therefore, our planet. Many applications of semantic segmentation were designed to operate in urban areas. However, fewer applications h
Autor:
Matheus M. dos Santos, Paulo Drews, Pedro Ribeiro, Marcelo Pias, Lucas M. Longaray, Silvia Silva da Costa Botelho, Giovanni G. De Giacomo
Publikováno v:
ICMLA
Forward-looking sonars (FLS) are perception sensors that are not affected by underwater turbidity. FLS are used in Remotely Operated Vehicles (ROVs) to help them in the tasks of exploration, navigation and region mapping. Besides the advantages of wo
Publikováno v:
2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (WRE).
This paper presents a convolutional neural network that is able to minimize the effects of poorly exposed digital images in post processing, outperforming state-of-the-art networks on two different conditions: images that are too dark, and images whe
Publikováno v:
BRACIS
Convolutional Neural Networks became a state-of-the-art approach for many different problems of computer vision, pattern recognition, and image processing. However, due to the large number of parameters of these architectures, researchers may find di
Autor:
Graçaliz Pereira Dimuro, Camila Alves Dias, Silvia Silva da Costa Botelho, Paulo Lilles Jorge Drews Junior, Jéssica C. S. Bueno, Humberto Bustince, Javier Fernández, Eduardo Nunes Borges, Giancarlo Lucca
Publikováno v:
Communications in Computer and Information Science ISBN: 9783319953113
NAFIPS
NAFIPS
This paper aims to introduce the proposal of replacing the usual pooling functions by the Choquet integral in Deep Learning Networks. The Choquet integral is an aggregation function studied and applied in several areas, as, e.g., in classification pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ed9dada51e230650f6076b425c108e2
https://doi.org/10.1007/978-3-319-95312-0_13
https://doi.org/10.1007/978-3-319-95312-0_13
Autor:
Paulo Drews, Silvia Silva da Costa Botelho, Jos Bratti, glen Protas, Joel Felipe de Oliveira Gaya
Publikováno v:
ICMLA
In recent years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many image restoration applications. The knowledge of how these models work, however, is still limited. While there have been many attempts at better
Publikováno v:
SIBGRAPI
Image dehazing can be described as the problem of mapping from a hazy image to a haze-free image. Most approaches to this problem use physical models based on simplifications and priors. In this work we demonstrate that a convolutional neural network