Few-ShotContinualActiveLearningbyaRobot
–Neural Information Processing Systems
The framework also uses uncertainty measures on the Gaussian representations of thepreviously learned classes tofindthemost informativesamples tobelabeled in an increment. We evaluate our approach on the CORe-50 dataset and on a real humanoid robot for the object classification task.
Neural Information Processing Systems
Feb-11-2026, 20:12:42 GMT
- Country:
- North America
- Canada (0.04)
- United States (0.04)
- North America
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Education (0.46)
- Technology: