Hi everyone! For those who don't know me yet, my name is Francois, I'm a research scientist at Meta. I'm passionate about explaining advanced ai concepts and making them more accessible.
Today, we are going to dive into one of the most significant contributions in the field of Computer Vision: the Vision Transformer (ViT).
The Vision Transformer was introduced by Alexey Dosovitskiy and others (Google Brain) in 2021 in the article A picture is worth 16×16 wordsAt the time, Transformers had proven to be the key to achieving great performance in NLP tasks, introduced in the essential article Attention is all you need in 2017.
Between 2017 and 2021, there were several attempts to integrate the attention mechanism into convolutional neural networks (CNNs). However, these were mostly hybrid models (combining CNN layers with attention layers) and lacked scalability. Google addressed this problem by removing convolutions altogether and leveraging their computational power to scale the model.
