Deep ensemble learning model based on covariance pooling of multi-layer cnn features

S Akodad, L Bombrun, M Puscasu, J **a… - … on Image Processing …, 2022 - ieeexplore.ieee.org
Compared to standard deep convolutional neural networks (CNN) which include a global
average pooling operator, second-order neural networks have a global covariance pooling …

Remote sensing scene classification based on covariance pooling of multi-layer cnn features guided by saliency maps

S Akodad, L Bombrun, C Germain… - … Conference on Pattern …, 2022 - Springer
The new generation of remote sensing imaging sensors enables high spatial, spectral and
temporal resolution images with high revisit frequencies. These sensors allow the …

Hyperspectral image classification using neural networks with effect of feature optimization on fused convolutional features

R Gadhave, RR Sedamkar, S Alegavi - AIP Conference Proceedings, 2023 - pubs.aip.org
Analysis of data and synthesis for hyper spectral imaging (HSI) is a new branch of remotely
sensed data and planet surveillance technologies. Classification techniques with the help of …

Ensemble learning methods on the space of covariance matrices: application to remote sensing scene and multivariate time series classification

S Akodad - 2021 - theses.hal.science
In view of the growing success of second-order statistics in classification problems, the work
of this thesis has been oriented towards the development of learning methods in manifolds …