2 citations · 4 across the 3 of their papers we have counts for
3 papers
A Metacognitive Approach to Out-of-Distribution Detection for Segmentation
Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper +1
Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open wor…
CompoSuite: A Compositional Reinforcement Learning Benchmark
Jorge A. Mendez, Marcel Hussing, Meghna Gummadi +1
We present CompoSuite, an open-source simulated robotic manipulation benchmark for compositional multi-task reinforcement learning (RL). Each CompoSuite task requires a particular…
SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries
Meghna Gummadi, David Kent, Jorge A. Mendez +1
While deep neural networks (DNNs) have achieved impressive classification performance in closed-world learning scenarios, they typically fail to generalize to unseen categories in…