Progressive Self-supervised Multi-objective NAS for Image Classification

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Garcia-Garcia:2024:evoapplications,

• author = "Cosijopii Garcia-Garcia and Alicia Morales-Reyes and Hugo Jair Escalante",
• title = "Progressive Self-supervised Multi-objective NAS for Image Classification",
• booktitle = "27th International Conference, EvoApplications 2024",
• year = "2024",
• editor = "Stephen Smith and Joao Correia and Christian Cintrano",
• series = "LNCS",
• volume = "14635",
• publisher = "Springer",
• address = "Aberystwyth",
• month = "3-5 " # apr,
• pages = "180--195",
• organisation = "EvoStar, Species",
• keywords = "genetic algorithms, genetic programming, cartesian genetic programming, ANN, MOGA, NSGA II, Evolutionary neural architecture search, AutoML, Evolutionary self-supervised learning",
• isbn13 = "978-3-031-56854-1",
• URL = "https://rdcu.be/dD0hO",
• DOI = "doi:10.1007/978-3-031-56855-8_11",
• abstract = "We introduce a novel progressive self-supervised framework for neural architecture search. Our aim is to search for competitive, yet significantly less complex, generic CNN architectures that can be used for multiple tasks (i.e., as a pretrained model). This is achieved through cartesian genetic programming (CGP) for neural architecture search (NAS). Our approach integrates self-supervised learning with a progressive architecture search process. This synergy unfolds within the continuous domain which is tackled via multi-objective evolutionary algorithms (MOEAs). To empirically validate our proposal, we adopted a rigorous evaluation using the non-dominated sorting genetic algorithm II (NSGA-II) for the CIFAR-100, CIFAR-10, SVHN and CINIC-10 datasets. The experimental results showcase the competitiveness of our approach in relation to state-of-the-art proposals concerning both classification performance and model complexity. Additionally, the effectiveness of this method in achieving strong generalization can be inferred.",
• notes = "http://www.evostar.org/2024/ EvoApplications2024 held in conjunction with EuroGP'2024, EvoCOP2024 and EvoMusArt2024",

}

Genetic Programming entries for Cosijopii Garcia-Garcia Alicia Morales-Reyes Hugo Jair Escalante

Citations