One-Shot Transfer of Affordance Regions? AffCorrs!

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.

Cite

Text

Hadjivelichkov et al. "One-Shot Transfer of Affordance Regions? AffCorrs!." Conference on Robot Learning, 2022.

Markdown

[Hadjivelichkov et al. "One-Shot Transfer of Affordance Regions? AffCorrs!." Conference on Robot Learning, 2022.](https://mlanthology.org/corl/2022/hadjivelichkov2022corl-oneshot/)

BibTeX

@inproceedings{hadjivelichkov2022corl-oneshot,
  title     = {{One-Shot Transfer of Affordance Regions? AffCorrs!}},
  author    = {Hadjivelichkov, Denis and Zwane, Sicelukwanda and Agapito, Lourdes and Deisenroth, Marc Peter and Kanoulas, Dimitrios},
  booktitle = {Conference on Robot Learning},
  year      = {2022},
  pages     = {550-560},
  volume    = {205},
  url       = {https://mlanthology.org/corl/2022/hadjivelichkov2022corl-oneshot/}
}