This is not the latest version of this item. The latest version can be found here.
An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale
| dc.contributor.author | Dosovitskiy, Alexey | |
| dc.contributor.author | Beyer, Lucas | |
| dc.contributor.author | Kolesnikov, Alexander | |
| dc.contributor.author | Weissenborn, Dirk | |
| dc.contributor.author | Zhai, Xiaohua | |
| dc.contributor.author | Unterthiner, Thomas | |
| dc.contributor.author | Dehghani, Mostafa | |
| dc.contributor.author | Minderer, Matthias | |
| dc.contributor.author | Heigold, Georg | |
| dc.contributor.author | Gelly, Sylvain | |
| dc.contributor.author | Uszkoreit, Jakob | |
| dc.contributor.author | Houlsby, Neil | |
| dc.date.accessioned | 2025-06-02T10:57:35Z | |
| dc.date.available | 2025-06-02T10:57:35Z | |
| dc.date.issued | 2020-10-22 | |
| dc.description | CNN 없이 이미지 패치를 Transformer Encoder에 적용하여 대규모 이미지 인식 성능을 보여주며, ViT가 컴퓨터 비전에서도 경쟁력 있음을 입증했습니다. | |
| dc.description.abstract | While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train. | |
| dc.identifier.uri | https://arxiv.org/pdf/2010.11929 | |
| dc.identifier.uri | http://data.inu.ac.kr/handle/123456789/1935 | |
| dc.language.iso | en_US | |
| dc.publisher | arXiv | |
| dc.title | An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale | |
| dc.title.alternative | VIT | |
| dc.type | Article |