Hadjivelichkov, D;
Deisenroth, MP;
Zwane, S;
Agapito, L;
Kanoulas, D;
(2023)
One-Shot Transfer of Affordance Regions? AffCorrs!
In:
Proceedings of The 6th Conference on Robot Learning.
(pp. pp. 550-560).
Proceedings of Machine Learning Research (PMLR): Auckland, New Zealand.
Preview |
Text
hadjivelichkov23a.pdf - Published Version Download (3MB) | Preview |
Abstract
In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance regions, we segment semantically corresponding parts within a target scene. We propose AffCorrs, an unsupervised model that combines the properties of pre-trained DINO-ViT's image descriptors and cyclic correspondences. We use AffCorrs to find corresponding affordances both for intra- and inter-class one-shot part segmentation. This task is more difficult than supervised alternatives, but enables future work such as learning affordances via imitation and assisted teleoperation. Project page with code and dataset: https://sites.google.com/view/affcorrs.
| Type: | Proceedings paper |
|---|---|
| Title: | One-Shot Transfer of Affordance Regions? AffCorrs! |
| Event: | 6th Conference on Robot Learning (CoRL 2022) |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v205/hadjivelichkov2... |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. |
| Keywords: | One-Shot, Affordance, Correspondence |
| 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/10174468 |
Archive Staff Only
 |
View Item |
