- author = "Ricardo Henrique Remes {de Lima} and Aurora Pozo and Alexander Mendiburu and Roberto Santana",
- title = "Automatic Design of Deep Neural Networks Applied to Image Segmentation Problems",
- booktitle = "EuroGP 2021: Proceedings of the 24th European Conference on Genetic Programming",
- year = "2021",
- editor = "Ting Hu and Nuno Lourenco and Eric Medvet",
- series = "LNCS",
- volume = "12691",
- publisher = "Springer Verlag",
- address = "Virtual Event",
- pages = "98--113",
- month = "7-9 " # apr,
- organisation = "EvoStar, Species",
- note = "Best paper candidate",
- keywords = "genetic algorithms, genetic programming, Grammatical evolution, DSGE, Neural architecture search, Deep learning, Edge detection, ANN",
- isbn13 = "978-3-030-72811-3",
-
DOI = "
doi:10.1007/978-3-030-72812-0_7",
- abstract = "A U-Net is a convolutional neural network mainly used for image segmentation domains such as medical image analysis. As other deep neural networks, the U-Net architecture influences the efficiency and accuracy of the network. We propose the use of a grammar-based evolutionary algorithm for the automatic design of deep neural networks for image segmentation tasks. The approach used is called Dynamic Structured Grammatical Evolution (DSGE), which employs a grammar to define the building blocks that are used to compose the networks, as well as the rules that help build them. We perform a set of experiments on the BSDS500 and ISBI12 datasets, designing networks tuned to image segmentation and edge detection. Subsequently, by using image similarity metrics, the results of our best performing networks are compared with the original U-Net. The results show that the proposed approach is able to design a network that is less complex in the number of trainable parameters, while also achieving slightly better results than the U-Net with a more consistent training.",
-
notes = "See also \cite{Lima:2022:GPEM}
Image segmentation, binary, multi-objects. GE to define structure of feedforward ANN (U-Net). Grammar to define U-Net structure. Automatic addition of matching up (on right of U) for each level on left of U.
DSGE restricted crossover cut points.
http://www.evostar.org/2021/eurogp/ Part of \cite{Hu:2021:GP} EuroGP'2021 held in conjunction with EvoCOP2021, EvoMusArt2021 and EvoApplications2021",
