Neural architecture search for image saliency fusion
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @Article{BIANCO:2020:IF,
-
author = "Simone Bianco and Marco Buzzelli and
Gianluigi Ciocca and Raimondo Schettini",
-
title = "Neural architecture search for image saliency fusion",
-
journal = "Information Fusion",
-
volume = "57",
-
pages = "89--101",
-
year = "2020",
-
ISSN = "1566-2535",
-
DOI = "doi:10.1016/j.inffus.2019.12.007",
-
URL = "http://www.sciencedirect.com/science/article/pii/S1566253519302374",
-
keywords = "genetic algorithms, genetic programming, Saliency
fusion, Evolutionary algorithms, Neural architecture
search",
-
abstract = "Saliency detection methods proposed in the literature
exploit different rationales, visual clues, and
assumptions, but there is no single best saliency
detection algorithm that is able to achieve good
results on all the different benchmark datasets. In
this paper we show that fusing different saliency
detection algorithms together by exploiting neural
network architectures makes it possible to obtain
better results. Designing the best architecture for a
given task is still an open problem since the existing
techniques have some limits with respect to the problem
formulation, to the search space, and require very high
computational resources. To overcome these problems, in
this paper we propose a three-step fusion approach. In
the first step, genetic programming techniques are
exploited to combine the outputs of existing saliency
algorithms using a set of provided operations. Having a
discrete search space allows us a fast generation of
the candidate solutions. In the second step, the
obtained solutions are converted into backbone
Convolutional Neural Networks (CNNs) where operations
are all implemented with differentiable functions,
allowing an efficient optimization of the corresponding
parameters (in a continuous space) by backpropagation.
In the last step, to enrich the expressiveness of the
initial architectures, the networks are further
extended with additional operations on intermediate
levels of the processing that are once again
efficiently optimized through backpropagation.
Extensive experimental evaluations show that the
proposed saliency fusion approach outperforms the
state-of-the-art on the MSRAB dataset and it is able to
generalize to unseen data of different benchmark
datasets",
- }
Genetic Programming entries for
Simone Bianco
Marco Buzzelli
Gianluigi Ciocca
Raimondo Schettini
Citations