Nested-TNT: Hierarchical Vision Transformers with Multi-Scale Feature Processing

arXiv:2404.13434v1 Announce Type: new
Abstract: Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into several local patches, known as "visual sentences". However, the information contained in the image is vast and complex, and focusing only on the features at the "visual sentence" level is not enough. The features between local patches should also be taken into …

abstract art arxiv computer computer vision convolutional neural networks cs.ai cs.cv feature hierarchical however image information language language processing natural natural language natural language processing networks neural networks performance processing scale state the information transformer transformers type vision vision transformers visual vit