Automatic Meta-Feature Engineering for CNN Fusion in Aerial Scene Classification Task

Autor(es)

de Melo, Vinicius V. ^[1] ; Sotto, Leo F. D. P. ^[1] ; Leonardo, Matheus M. ^[1] ; Faria, Fabio A. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Fed Sao Paulo, Inst Sci & Technol, BR-04021001 Sao Jose Dos Campos - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE Geoscience and Remote Sensing Letters; v. 17, n. 9, p. 1652-1656, SEPT 2020.
• Citações Web of Science: 0

Resumo

The aerial scene-classification task is a challenging problem to remote sensing area with important applicability to civil and military affairs. A technique that has achieved excellent results in this task is the convolutional neural network (CNN). CNNs are powerful semantic-level feature-extraction techniques successfully applied to many application domains. Nevertheless, many works in the literature have shown that a single CNN cannot solve all kinds of application domains properly. Hence, an alternative solution might be the joining of CNN architectures as an ensemble of classifiers. In this sense, this letter proposes a new strategy of deep feature-based classifier fusion through a meta-feature engineering approach based on the Kaizen programming (KP) technique for the aerial scene-classification task. KP is a technique that continuously improves partial solutions and combines them into a complete solution. In the context, a partial solution is a meta-feature, and a complete solution is an ensemble of classifiers. In our experiments on three different public data sets, we show that KP can automatically engineer meta-features that significantly improve the performance of a stacked classifier while reducing the number of total meta-features. (AU)

• Processo FAPESP: 18/13202-4 - Desenvolvimento de um algoritmo de programação genética linear usando algoritmos de estimação de distribuição aplicado a aprendizado de máquina supervisionado
• Beneficiário: Léo Françoso Dal Piccol Sotto
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado Direto
• Processo FAPESP: 16/07095-5 - Desenvolvimento da técnica programação genética linear probabilística e aplicação em programação Kaizen para aprendizado de máquina supervisionado
• Beneficiário: Léo Françoso Dal Piccol Sotto
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto