The Vision Transformer Model

With the Transformer architecture revolutionizing the implementation of attention, and achieving very promising results in the natural language processing domain, it was only a matter of time before we could see its application in the computer vision domain too. This was eventually achieved with the implementation of the Vision Transformer (ViT). In this tutorial, you will discover the architecture of the Vision Transformer model, and its application to the task of image classification. The Vision Transformer Model Photo by Paul Skorupskas, some rights reserved. We had seen how the emergence of the Transformer architecture of Vaswani et al. (2017) has revolutionized the use of attention, without relying on recurrence and convolutions as earlier attention models had previously done.