arXiv (Cornell University)· 2020· Preprint
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- 21,699citations
- 2020year
Short summary
A pure Transformer architecture, Vision Transformer (ViT), directly applied to sequences of image patches achieves state-of-the-art results in image classification, outperforming convolutional networks with fewer computational resources for training.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduced Vision Transformer (ViT), a pure Transformer model for image classification.
- ViT processes images by dividing them into sequences of fixed-size patches.
- Achieved excellent results on multiple image recognition benchmarks (ImageNet, CIFAR-100, VTAB).
- Outperformed state-of-the-art convolutional networks.
- Required substantially fewer computational resources for training compared to CNNs.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source. arXiv (Cornell University), 2020 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science