Object Detection on Habitat Gibson Specialization 1.0 (val)
41.23Box AP50SEAL
Evaluation results
| Method | Links | |
|---|---|---|
| SEALAction Policy=Gainful Curiosity, Perception Baseline=3DLabelProp2021.12 | 41.23 | |
| Active Neural SLAM + Optical FlowAction Policy=Active Neural SLAM, Perception Baseline=Optical Flow2021.12 | 35.9 | |
| Semantic Curiosity + Optical FlowAction Policy=Semantic Curiosity, Perception Baseline=Optical Flow2021.12 | 35.71 | |
| Semantic Curiosity + Self-trainingAction Policy=Semantic Curiosity, Perception Baseline=Self-training2021.12 | 35.23 | |
| Active Neural SLAM + Self-trainingAction Policy=Active Neural SLAM, Perception Baseline=Self-training2021.12 | 34.84 | |
| Pretrained Mask-RCNNState=Pretrained2021.12 | 34.82 | |
| Random Policy + Optical FlowAction Policy=Random Policy, Perception Baseline=Optical Flow2021.12 | 34.33 | |
| Frontier Exploration + Optical FlowAction Policy=Frontier Exploration, Perception Baseline=Optical Flow2021.12 | 34.19 | |
| Random Policy + Self-trainingAction Policy=Random Policy, Perception Baseline=Self-training2021.12 | 34.11 | |
| Frontier Exploration + Self-trainingAction Policy=Frontier Exploration, Perception Baseline=Self-training2021.12 | 33.29 |