On what sets CenterNet apart from other object-detection architectures

Wet dog heat map. Source:

CenterNet is an anchorless object detection architecture. This structure has an important advantage in that it replaces the classical NMS (Non Maximum Suppression) at the post process, with a much more elegant algorithm, that is natural to the CNN flow. This mechanism enables a much faster inference. See Fig. 1.

Yolo-V3 detections. Image Source:

In this post we’ll discuss the YOLO detection network and its versions 1, 2 and especially 3.

In 2016 Redmon, Divvala, Girschick and Farhadi revolutionized object detection with a paper titled: . In the paper they introduced a new approach to object detection…

Object detection in images is a common task in computer vision. Its use cases vary from missile guidance to automated production lines, console games and cleaning robots. Object detection algorithms in computer vision have been around long before their migration to deep learning:

In the 2001 paper

Training. Source:

In this post we will explore the mechanism of neural network training, but I’ll do my best to avoid rigorous mathematical discussions and keep it intuitive.

Consider the following task: you receive an image, and want an algorithm that returns (predicts) the correct number of people in the image.


A Space Divided. Image source:

Perceptron is the most basic form of a neural network and therefor a good place to start. Perceptrons are a type of binary classifiers — given data representing some object as an input, a perceptron determines to which class the object belongs. It is called ‘binary’ because it only has…

Practical Problems. Image source:

At the end of the first post I wrote that next we’d be learning a basic neural network, but later I realized that there should come another section, which discusses artificial intelligence from the mathematical aspect. …

Image source:

If you’ve heard about neural networks and are not sure what they are, if you’re interested in artificial intelligence and how it ‘learns by itself’ to perform complex tasks for autonomous driving, healthcare, product quality assurance etc., …

Uri Almog

A machine learning engineer writing about computer vision. Loves to trek, scubadive, visual arts and combinations thereof.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store