Object Detection on Habitat Gibson Generalization 1.0 (val)
40.02AP50 (Box)SEAL
Evaluation results
| Method | Links | |
|---|---|---|
| SEALAction Policy=Gainful Curiosity, Perception Baseline=3DLabelProp2021.12 | 40.02 | |
| Active Neural SLAM + Optical FlowAction Policy=Active Neural SLAM, Perception Baseline=Optical Flow2021.12 | 35.85 | |
| Semantic Curiosity + Optical FlowAction Policy=Semantic Curiosity, Perception Baseline=Optical Flow2021.12 | 35.61 | |
| Frontier Exploration + Optical FlowAction Policy=Frontier Exploration, Perception Baseline=Optical Flow2021.12 | 35.22 | |
| Semantic Curiosity + Self-trainingAction Policy=Semantic Curiosity, Perception Baseline=Self-training2021.12 | 35.04 | |
| Pretrained Mask-RCNNState=Pretrained2021.12 | 34.82 | |
| Active Neural SLAM + Self-trainingAction Policy=Active Neural SLAM, Perception Baseline=Self-training2021.12 | 34.35 | |
| Random Policy + Optical FlowAction Policy=Random Policy, Perception Baseline=Optical Flow2021.12 | 33.97 | |
| Frontier Exploration + Self-trainingAction Policy=Frontier Exploration, Perception Baseline=Self-training2021.12 | 33.78 | |
| Random Policy + Self-trainingAction Policy=Random Policy, Perception Baseline=Self-training2021.12 | 33.41 |