One-Shot Transfer of Affordance Regions? AffCorrs!
One-Shot Transfer of Affordance Regions? AffCorrs!
复制标题
DOI:
10.48550/arxiv.2209.07147
复制
发表时间:
2022-09
期刊:
影响因子:
--
通讯作者:
Denis Hadjivelichkov;Sicelukwanda Zwane;M. Deisenroth;L. Agapito;D. Kanoulas
中科院分区:
文献类型:
--
作者:
Denis Hadjivelichkov;Sicelukwanda Zwane;M. Deisenroth;L. Agapito;D. Kanoulas
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.