deep-learningCNNessentialsclassification

VggNet: Very Deep Convolutional Networks for Large-Scale Image Recognition

Reviewed on Mar 16, 2017 • https://arxiv.org/pdf/1409.1556.pdf

Reference : K. Simonyan, A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of ICLR 2015, p.1-14.

Winner of the 2014 edition of the ImageNet classification challenge (ILSVRC-2014). The authors proposed 6 networks similar but deeper than the AlexNet configuration. They show that the 16-layer and the 19-layer models and the best ones. The main novelty with this paper is the use of small 3x3 filters in a deeper architecture.