Hadjivelichkov, D;
Kanoulas, D;
(2021)
Fully Self-Supervised Class Awareness in Dense Object Descriptors.
In:
Proceedings of the 5th Conference on Robot Learning.
(pp. pp. 1522-1531).
PMLR: London, UK.
Preview |
Text
CoRL_2021_Denis_final.pdf - Accepted Version Download (10MB) | Preview |
Abstract
We address the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes. The method introduces learning of class-aware dense object descriptors by providing either unsupervised discrete labels or confidence in object similarities. We quantitatively and qualitatively show that the introduced method outperforms previous techniques with more robust pixel-to-pixel matches. An example robotic application is also shown - grasping of objects in clutter based on corresponding points.
| Type: | Proceedings paper |
|---|---|
| Title: | Fully Self-Supervised Class Awareness in Dense Object Descriptors |
| Event: | 2021 Conference on Robot Learning (CoRL) |
| Location: | London, UK |
| Dates: | 08 November 2021 - 11 September 2021 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v164/hadjivelichkov2... |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10135216 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
