Swin

Vision Transformer (ViT) outperformed convolutional neural networks in image classification, but it required more training data. New work enabled ViT and its variants to outperform other architectures with less training data.

Equipment that relies on computer vision while unplugged — mobile phones, drones, satellites, autonomous cars — need power-efficient models. A new architecture set a record for accuracy per computation.

The transformer architecture is notoriously inefficient when processing long sequences — a problem in processing images, which are essentially long sequences of pixels. One way around this is to break up input images and process the pieces