A Data-Efficient Image Transformer is a type of Vision Transformer for image classification tasks. The model is trained using a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention.
Source: Training data-efficient image transformers & distillation through attentionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 23 | 20.91% |
Object Detection | 10 | 9.09% |
Semantic Segmentation | 8 | 7.27% |
Quantization | 7 | 6.36% |
Self-Supervised Learning | 5 | 4.55% |
Efficient ViTs | 4 | 3.64% |
Fine-Grained Image Classification | 4 | 3.64% |
Document Image Classification | 3 | 2.73% |
Document Layout Analysis | 3 | 2.73% |