One-Shot Transfer of Affordance Regions? AffCorrs!

Denis Hadjivelichkov, Sicelukwanda Zwane, Lourdes Agapito, Marc Peter Deisenroth, Dimitrios Kanoulas
Proceedings of The 6th Conference on Robot Learning, PMLR 205:550-560, 2023.

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 this Paper

BibTeX
@InProceedings{pmlr-v205-hadjivelichkov23a, 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 = {Proceedings of The 6th Conference on Robot Learning}, pages = {550--560}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/hadjivelichkov23a/hadjivelichkov23a.pdf}, url = {https://proceedings.mlr.press/v205/hadjivelichkov23a.html}, 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.} }
Endnote
%0 Conference Paper %T One-Shot Transfer of Affordance Regions? AffCorrs! %A Denis Hadjivelichkov %A Sicelukwanda Zwane %A Lourdes Agapito %A Marc Peter Deisenroth %A Dimitrios Kanoulas %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-hadjivelichkov23a %I PMLR %P 550--560 %U https://proceedings.mlr.press/v205/hadjivelichkov23a.html %V 205 %X 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.
APA
Hadjivelichkov, D., Zwane, S., Agapito, L., Deisenroth, M.P. & Kanoulas, D.. (2023). One-Shot Transfer of Affordance Regions? AffCorrs!. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:550-560 Available from https://proceedings.mlr.press/v205/hadjivelichkov23a.html.

Related Material