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 | 52 | 5.50% |
| Semantic Segmentation | 51 | 5.40% |
| Object Detection | 36 | 3.81% |
| Self-Supervised Learning | 27 | 2.86% |
| Decoder | 23 | 2.43% |
| Image Segmentation | 21 | 2.22% |
| Classification | 21 | 2.22% |
| Computational Efficiency | 16 | 1.69% |
| Language Modelling | 14 | 1.48% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Attention
|
Attention Mechanisms | |
Dense Connections
|
Feedforward Networks | |
Layer Normalization
|
Normalization | |
Multi-Head Attention
|
Attention Modules | |
Residual Connection
|
Skip Connections |
