Vision Transformer

Anonymous

Keywords: Vision transformer(ViT), self-attention, deep learning

Abstract: In last 10 years there has been significant development in Computer vision after development of Convolutional neural network(ConvNets). There has been research around combining self-attention with CNN after success seen in NLP with transformer models. In the blog-post we discuss the model “Vision transformer”(ViT) in detail and its new intuitions.

ICLR Paper: https://openreview.net/forum?id=YicbFdNTTy