SIBGRAPI 2017 Tutorial

Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask

An overview of Deep Learning methods for Computer Vision with applications

Authors: Moacir A. Ponti 1, Leonardo S. F. Ribeiro 1, Tiago S. Nazare 1, Tu Bui 2, John Collomosse 2

(1) ICMC - Universidade de São Paulo (2) CVSSP - University of Surrey

Materials, Slides, Papers, etc.:

• Link to the Tutorial Webpage with Slides and Others
• Link to the Tutorial Paper

Source-Code in TensorFlow using MNIST Classification Dataset

1. ShallowNet: shallow network with input and output layers
2. DeepNet: deep network with two hidden dense (fully connected) layers
3. DeepConvNet: deep network with two hidden layers, one convolutional, one fully connected)