Image Models
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 |
|---|---|---|
| Semantic Segmentation | 57 | 5.75% |
| Image Classification | 54 | 5.45% |
| Object Detection | 41 | 4.14% |
| Self-Supervised Learning | 26 | 2.62% |
| Decoder | 23 | 2.32% |
| Image Segmentation | 23 | 2.32% |
| Object | 23 | 2.32% |
| Classification | 21 | 2.12% |
| Computational Efficiency | 18 | 1.82% |
Dense Connections
Layer Normalization
Multi-Head Attention
Residual Connection
Scaled Dot-Product Attention
