What is ViTs?

ViTs, or Vision Transformers, are a type of neural network architecture that applies the Transformer model (originally designed for natural language processing) to image recognition tasks. Instead of processing images as a grid of pixels using convolutional layers (as in CNNs), ViTs split an image into patches and treat these patches as a sequence of "words" which are then fed into a Transformer encoder. This allows the model to capture global relationships between image regions, often achieving state-of-the-art performance in image classification and other vision tasks. They are commonly used in applications such as image classification, object detection, and semantic segmentation.