Understanding SSD MultiBox -- Real-Time Object Detection In Deep Learning

Since AlexNet took the research world by storm at the 2012 ImageNet Large-Scale Visual Recognition Challenge (ILSVRC), deep learning has become the go-to method for image recognition tasks, far surpassing more traditional computer vision methods used in the literature. In the field of computer vision, convolution neural networks excel at image classification, which consists of categorising images, given a set of classes (e.g. Nowadays, deep learning networks are better at image classification than humans, which shows just how powerful this technique is. However, we as humans do far more than just classify images when observing and interacting with the world. We also localize and classify each element within our field of view.