The 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 ScalePaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 85 | 9.55% |
Image Classification | 63 | 7.08% |
Object Detection | 34 | 3.82% |
Self-Supervised Learning | 33 | 3.71% |
Decoder | 26 | 2.92% |
Image Segmentation | 23 | 2.58% |
Classification | 18 | 2.02% |
Instance Segmentation | 16 | 1.80% |
Retrieval | 15 | 1.69% |