Vision Transformer: Vit and its Derivatives
This is an incremental review paper summarizing existing work on ViT and its applications across fields.
The paper reviews Vision Transformer (ViT) and its derivatives, which apply transformer architectures to computer vision tasks, achieving strong performance on benchmarks like ImageNet, COCO, and ADE20k.
Transformer, an attention-based encoder-decoder architecture, has not only revolutionized the field of natural language processing (NLP), but has also done some pioneering work in the field of computer vision (CV). Compared to convolutional neural networks (CNNs), the Vision Transformer (ViT) relies on excellent modeling capabilities to achieve very good performance on several benchmarks such as ImageNet, COCO, and ADE20k. ViT is inspired by the self-attention mechanism in natural language processing, where word embeddings are replaced with patch embeddings. This paper reviews the derivatives of ViT and the cross-applications of ViT with other fields.