Vision
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Task Unlearning | 8 vision tasks | Target Accuracy58.9 | 15 | |
| Multimodal Reasoning | Vision R1 (test) | Accuracy58.75 | 12 | |
| Image Classification | Vision-Few-Shot 12-dataset suite 4-shot | PETS Accuracy92.2 | 10 | |
| Task Negation | 14-Vision | Target Accuracy57.8 | 8 | |
| Cardiac PET kinetic parameter estimation | Siemens Vision 450 (Rest) | K1 (ml/min/g)0.78 | 5 | |
| Camera Model Identification | VISION YouTube | Accuracy93.51 | 2 | |
| Camera Model Identification | VISION WhatsApp | Accuracy93.68 | 2 | |
| Camera Model Identification | VISION (Native) | Accuracy94.77 | 2 |
Showing 8 of 8 rows