Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Jordao, Artur"'
Layer pruning offers a promising alternative to standard structured pruning, effectively reducing computational costs, latency, and memory footprint. While notable layer-pruning approaches aim to detect unimportant layers for removal, they often rely
Externí odkaz:
http://arxiv.org/abs/2411.14345
Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the field. Exte
Externí odkaz:
http://arxiv.org/abs/2405.17081
Pruning is a standard technique for reducing the computational cost of deep networks. Many advances in pruning leverage concepts from the Lottery Ticket Hypothesis (LTH). LTH reveals that inside a trained dense network exists sparse subnetworks (tick
Externí odkaz:
http://arxiv.org/abs/2301.10835
Autor:
Jordao, Artur, Pedrini, Helio
Pruning is a well-known mechanism for reducing the computational cost of deep convolutional networks. However, studies have shown the potential of pruning as a form of regularization, which reduces overfitting and improves generalization. We demonstr
Externí odkaz:
http://arxiv.org/abs/2108.04890
Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These architectures consist of stages, which are sets of layers that operate on representations in the same resolutio
Externí odkaz:
http://arxiv.org/abs/2004.11178
Dimensionality reduction plays an important role in computer vision problems since it reduces computational cost and is often capable of yielding more discriminative data representation. In this context, Partial Least Squares (PLS) has presented nota
Externí odkaz:
http://arxiv.org/abs/1910.02319
Autor:
Jordao, Artur, Souza, Joao Paulo da Ponte, Kuroda, Michelle Chaves, de Rezende, Marcelo Fagundes, Pedrini, Helio, Vidal, Alexandre Campane
Publikováno v:
In Journal of Applied Geophysics May 2023 212
Publikováno v:
British Machine Vision Conference Workshop, 2019
Modern pattern recognition methods are based on convolutional networks since they are able to learn complex patterns that benefit the classification. However, convolutional networks are computationally expensive and require a considerable amount of m
Externí odkaz:
http://arxiv.org/abs/1810.07610
Human activity recognition based on wearable sensor data has been an attractive research topic due to its application in areas such as healthcare and smart environments. In this context, many works have presented remarkable results using acceleromete
Externí odkaz:
http://arxiv.org/abs/1806.05226
The variety of pedestrians detectors proposed in recent years has encouraged some works to fuse pedestrian detectors to achieve a more accurate detection. The intuition behind is to combine the detectors based on its spatial consensus. We propose a n
Externí odkaz:
http://arxiv.org/abs/1806.03361