Data Augmentation and Convolutional Network Architecture Influence on Distributed Learning

• Victor Forattini Jansen UFV http://orcid.org/0009-0005-8179-1717
• Emanuel Teixeira Martins UFV https://orcid.org/0009-0005-5528-5036
• Yasmin Souza Lima UFV https://orcid.org/0009-0000-4963-4440
• Flavio de Oliveira Silva UMINHO / UFU https://orcid.org/0000-0001-7051-7396
• Rodrigo Moreira UFV https://orcid.org/0000-0002-9328-8618
• Larissa Ferreira Rodrigues Moreira UFV https://orcid.org/0000-0001-8947-9182

Resumo

Convolutional Neural Networks (CNNs) have proven to be highly effective in solving a broad spectrum of computer vision tasks, such as classification, identification, and segmentation. These methods can be deployed in both centralized and distributed environments, depending on the computational demands of the task. While much of the literature has focused on the explainability of CNNs, which is essential for building trust and confidence in their predictions, there remains a gap in understanding their impact on computational resources, particularly in distributed training contexts. In this study, we analyze how CNN architectures primarily influence model accuracy and investigate additional factors that affect computational efficiency in distributed systems. Our findings contribute valuable insights for optimizing the deployment of CNNs in resource-intensive scenarios, paving the way for further exploration of variables critical to distributed learning.

Palavras-chave: distributed learning, rice classification, data augumentation, CNN, factorial design