Autor(es)

Ponti, Moacir A. ; Ribeiro, Leonardo S. F. ; Nazare, Tiago S. ; Bui, Tu ; Collomosse, John ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2017 30TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES TUTORIALS (SIBGRAPI-T); v. N/A, p. 25-pg., 2017-01-01.

Resumo

Deep Learning methods are currently the state-of-the-art in many Computer Vision and Image Processing problems, in particular image classification. After years of intensive investigation, a few models matured and became important tools, including Convolutional Neural Networks (CNNs), Siamese and Triplet Networks, Auto-Encoders (AEs) and Generative Adversarial Networks (GANs). The field is fast-paced and there is a lot of terminologies to catch up for those who want to adventure in Deep Learning waters. This paper has the objective to introduce the most fundamental concepts of Deep Learning for Computer Vision in particular CNNs, AEs and GANs, including architectures, inner workings and optimization. We offer an updated description of the theoretical and practical knowledge of working with those models. After that, we describe Siamese and Triplet Networks, not often covered in tutorial papers, as well as review the literature on recent and exciting topics such as visual stylization, pixel-wise prediction and video processing. Finally, we discuss the limitations of Deep Learning for Computer Vision. (AU)

• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 17/10068-2 - Métodos de redução de dimensionalidade em representações geradas por redes convolucionais triplet
• Beneficiário: Leo Sampaio Ferraz Ribeiro
• Modalidade de apoio: Bolsas no Brasil - Iniciação Científica
• Processo FAPESP: 15/04883-0 - Detecção de eventos não usuais em vídeos de segurança
• Beneficiário: Tiago Santana de Nazare
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto