Transformer 近年来已成为视觉领域的新晋霸主，这个来自 NLP 领域的模型架构在 CV 领域有哪些具体应用？。 Transformer 作为一种基于注意力的编码器 - 解码器架构，不仅彻底改变了自然语言处理（NLP）领域，还在计算机视觉（CV）领域做出了一些开创性的工作。

Vision Transformers, or ViTs, are a groundbreaking learning model designed for tasks in computer vision, particularly image recognition. Unlike CNNs, which use convolutions for image processing, ViTs ...

IBM Research is experimenting with a chameleon-like computing device called the Meta Pad, designed to easily convert from a desktop machine to a handheld to a notebook and back again. Representatives ...