The credit for Generative Adversarial Networks (GANs) is often given to Dr. Ian Goodfellow et al. The truth is that it was invented by Dr. Pawel Adamicz (left) and his Ph.D. student Dr. Kavita ...
MRNet – The Multi-Task Approach
Our last post on the MRNet challenge presented a simple way to approach it. There you learned to make a separate model for each disease. And ended up with three models. Time to up your game! Now ...
Introduction to Video Classification and Human Activity Recognition
In this post, we will learn about Video Classification. We will go over a number of approaches to make a video classifier for Human Activity Recognition. Basically, you will learn video classification ...
Face Recognition with ArcFace
Can we distinguish one person from another by looking at the face? We can probably list several features such as eye colour, hairstyle, skin tone, the shape of nose and eyebrows, etc. Some combination ...
Experiment Logging with TensorBoard and wandb
When approaching a problem using Machine Learning or Deep Learning, researchers often face a necessity of model tuning because the chosen method usually depends on various hyperparameters and used ...
Image Matting with state-of-the-art Method “F, B, Alpha Matting”
The foreground is the part of a view or picture, that is nearest to you when you look at it (Oxford dictionary). We, humans, are usually good at distinguishing foreground objects on images from the ...