Title
Neural architecture search for image saliency fusion.
Abstract
•Neural architecture search addressed with Genetic Programming and Backpropagation.•Genetic Programming efficiently provides blueprints for neural network architectures.•Backpropagation significantly improves the performance of candidate blueprints.•Proper fusion of hand-crafted saliency methods can outperform deep learning methods.•Proper fusion of deep learning methods outperforms the state of the art.
Year
DOI
Venue
2020
10.1016/j.inffus.2019.12.007
Information Fusion
Keywords
Field
DocType
Saliency fusion,Evolutionary algorithms,Neural architecture search
Open problem,Evolutionary algorithm,Salience (neuroscience),Convolutional neural network,Genetic programming,Exploit,Artificial intelligence,Backpropagation,Artificial neural network,Machine learning,Mathematics
Journal
Volume
ISSN
Citations 
57
1566-2535
2
PageRank 
References 
Authors
0.35
0
4
Name
Order
Citations
PageRank
Simone Bianco122624.48
Marco Buzzelli2294.91
Gianluigi Ciocca336433.44
Raimondo Schettini41476154.06