Vision transformer

Also written: vision transformers, ViT

A transformer for images: it cuts the picture into small patches and treats each patch like a word.

Other terms from the same lesson

• channel: In images, one layer of numbers per pixel, such as red, green or blue. A CNN layer outputs one channel per filter.
• CNN: A network that slides small pattern-detectors across an image to find edges, shapes and objects.
• feature map: The grid of scores a CNN filter produces: high where its pattern appears in the image, low elsewhere.
• kernel: In a CNN, a small grid of weights that slides over an image and scores how strongly each patch matches a pattern, such as an edge.
• max pooling: Shrinking a feature map by keeping only the biggest value in each small square, so a pattern counts wherever it shows up nearby.
• padding: Extra zeros added around an image's edge so a CNN filter can be centered on edge pixels too, and the output shrinks less.
• stride: How many pixels a CNN filter moves at each step. A stride of 2 skips every other spot and halves the output size.