Vecerik, M;
Kay, J;
Hadsell, R;
Agapito, L;
Scholz, J;
(2022)
Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings.
In:
Proceedings - IEEE International Conference on Robotics and Automation.
(pp. pp. 1251-1257).
IEEE: Philadelphia, PA, USA.
Preview |
Text
De Agapito Vicente_2112.04910.pdf Download (5MB) | Preview |
Abstract
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint embeddings in a single forward pass, meaning the model is trained to track everything at once, or allocate their full capacity to a sparse predefined set of points, trading generality for accuracy. In this paper we explore a middle ground based on the observation that the number of relevant points at a given time are typically relatively few, e.g. grasp points on a target object. Our main contribution is a novel architecture, inspired by few-shot task adaptation, which allows a sparse-style network to condition on a keypoint embedding that indicates which point to track. Our central finding is that this approach provides the generality of dense-embedding models, while offering accuracy significantly closer to sparse-keypoint approaches. We present results illustrating this capacity vs. accuracy trade-off, and demonstrate the ability to zero-shot transfer to new object instances (within-class) using a real-robot pick-and-place task.
| Type: | Proceedings paper |
|---|---|
| Title: | Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings |
| Event: | 2022 International Conference on Robotics and Automation (ICRA) |
| Dates: | 23 May 2022 - 27 May 2022 |
| ISBN-13: | 9781728196817 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ICRA46639.2022.9812209 |
| Publisher version: | https://doi.org/10.1109/ICRA46639.2022.9812209 |
| 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. |
| Keywords: | Visualization, Computer vision, Three-dimensional displays, Target tracking, Robot vision systems, Reinforcement learning, Footwear |
| 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/10168445 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
