查看文章

A mobile vision transformer network for use on mobile devices, such as smart eyewear devices and other augmented reality (AR) and virtual reality (VR) devices. The mobile vision transformer network considers factors including number of parameters, latency, and model performance, as they reflect disk storage, mobile frames per second (FPS), and application quality, respectively. The mobile vision transformer network processes images, eg, for image classification, segmentation, and detection. The mobile vision transformer network has a fine-grained architecture including a search algorithm performing latency-driven slimming that jointly improves model size and speed.