ORBIT
Introduced by Massiceti et al. in ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
ORBIT is a real-world few-shot dataset and benchmark grounded in a real-world application of teachable object recognizers for people who are blind/low vision. The dataset contains 3,822 videos of 486 objects recorded by people who are blind/low-vision on their mobile phones, and the benchmark reflects a realistic, highly challenging recognition problem, providing a rich playground to drive research in robustness to few-shot, high-variation conditions.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
ORBIT Clutter Video Evaluation
|
ProtoNets + LITE
|
|||
|
ORBIT Clean Video Evaluation
|
SimpleCNAPs + LITE
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
