Name
Abstract | ||
|---|---|---|
We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful for robotics. The main contributions of this paper are: 1) a self-supervised model called Object-Contrastive Network (OCN) that can discover and disentangle object attributes from video without using any labels; 2) we leverage self-supervision for online adaptation: the longer our online model looks at objects in a video, the lower the object identification error, while the offline baseline remains with a large fixed error; 3) we show the usefulness of our approach for a robotic pointing task; a robot can point to objects similar to the one presented in front of it. Videos illustrating online object adaptation and robotic pointing are provided as supplementary material. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICRA40945.2020.9196567 | ICRA |
DocType | Volume | Issue |
Conference | 2020 | 1 |
Citations | PageRank | References |
0 | 0.34 | 12 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sören Pirk | 1 | 8 | 4.50 |
| Seyed Mohammad Khansari-Zadeh | 2 | 160 | 11.57 |
| Yunfei Bai | 3 | 92 | 9.48 |
| Corey Lynch | 4 | 9 | 3.17 |
| Pierre Sermanet | 5 | 1788 | 185.17 |