Vision Transformers
Vision Transformer
Introduced by Dosovitskiy et al. in An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleThe Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over patches of the image. An image is split into fixed-size patches, each of them are then linearly embedded, position embeddings are added, and the resulting sequence of vectors is fed to a standard Transformer encoder. In order to perform classification, the standard approach of adding an extra learnable “classification token” to the sequence is used.
Source: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 84 | 16.41% |
| Semantic Segmentation | 48 | 9.38% |
| Object Detection | 42 | 8.20% |
| Instance Segmentation | 15 | 2.93% |
| Self-Supervised Learning | 12 | 2.34% |
| Fine-Grained Image Classification | 10 | 1.95% |
| General Classification | 8 | 1.56% |
| Pose Estimation | 7 | 1.37% |
| Depth Estimation | 7 | 1.37% |
Dense Connections
Layer Normalization
Multi-Head Attention
Residual Connection
Scaled Dot-Product Attention
