by Michele Laurelli
Deep CNN architecture using small 3x3 filters throughout, emphasizing depth.
VGG-16 and VGG-19 with 16/19 layers. Simple, uniform architecture. Multiple 3x3 convs approximate larger receptive fields efficiently.
VGG-16 for transfer learning
Feature extraction backbone
ImageNet classification
A deep learning architecture specialized for processing grid-like data such as images, using convolutional layers.
A subset of machine learning using neural networks with multiple layers to learn hierarchical representations of data.
Large-scale image dataset with 14M images across 20k categories, used for ILSVRC competition.