1 code implementation • 24 Jan 2022 • Loris Nanni, Michelangelo Paci, Sheryl Brahnam, Alessandra Lumini
These novel methods are based on the Fourier Transform (FT), the Radon Transform (RT) and the Discrete Cosine Transform (DCT).
no code implementations • 24 Dec 2021 • Loris Nanni, Daniela Cuza, Alessandra Lumini, Andrea Loreggia, Sheryl Brahnam
Semantic segmentation consists in classifying each pixel of an image by assigning it to a specific label chosen from a set of all the available ones.
no code implementations • 9 Oct 2021 • Loris Nanni, Alessandra Lumini, Alessandro Manfe, Riccardo Rampon, Sheryl Brahnam, Giorgio Venturin
Multilabel learning tackles the problem of associating a sample with multiple class labels.
no code implementations • 28 Aug 2021 • Loris Nanni, Alessandro Manfe, Gianluca Maguolo, Alessandra Lumini, Sheryl Brahnam
The best performing ensemble, which combined the CNNs using the different augmentation methods and the two new Adam variants proposed here, achieved state of the art on both insect data sets: 95. 52% on Deng and 73. 46% on IP102, a score on Deng that competed with human expert classifications.
no code implementations • 8 Apr 2021 • Loris Nanni, Stefano Ghidoni, Sheryl Brahnam
Features play a crucial role in computer vision.
no code implementations • 29 Mar 2021 • Loris Nanni, Gianluca Maguolo, Sheryl Brahnam, Michelangelo Paci
Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs.
no code implementations • 22 Jan 2021 • Loris Nanni, Alessandra Lumini, Sheryl Brahnam
Motivation: Automatic Anatomical Therapeutic Chemical (ATC) classification is a critical and highly competitive area of research in bioinformatics because of its potential for expediting drug develop-ment and research.
no code implementations • 15 Jul 2020 • Loris Nanni, Gianluca Maguolo, Sheryl Brahnam, Michelangelo Paci
The best performing ensembles combining data augmentation techniques with different signal representations are compared and shown to outperform the best methods reported in the literature on these datasets.
no code implementations • 11 Jun 2019 • Loris Nanni, Alessandra Lumini, Federica Pasquali, Sheryl Brahnam
In this paper we address the problem of protein classification starting from a multi-view 2D representation of proteins.