MobileViT is a vision transformer that is tuned to mobile phone
Source: MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision TransformerPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 4 | 23.53% |
Object Detection | 4 | 23.53% |
Semantic Segmentation | 2 | 11.76% |
Computational Efficiency | 1 | 5.88% |
Crowd Counting | 1 | 5.88% |
Object Tracking | 1 | 5.88% |
Visual Object Tracking | 1 | 5.88% |
Self-Supervised Learning | 1 | 5.88% |
Benchmarking | 1 | 5.88% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |