Bongard-OpenWorld
Introduced by Wu et al. in Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
Bongard-OpenWorld is a new benchmark for evaluating real-world few-shot reasoning for machine vision. We hope it can help us better understand the limitations of current visual intelligence and facilitate future research on visual agents with stronger few-shot visual reasoning capabilities.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Bongard-OpenWorld
|
Human
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
