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:
ArXiv
影响因子:
--
通讯作者:
Denis Hadjivelichkov;Sicelukwanda Zwane;M. Deisenroth;L. Agapito;D. Kanoulas
Denis Hadjivelichkov;Sicelukwanda Zwane;M. Deisenroth;L. Agapito;D. Kanoulas
中科院分区:
其他
文献类型:
--
作者:
Denis Hadjivelichkov;Sicelukwanda Zwane;M. Deisenroth;L. Agapito;D. Kanoulas

文献摘要

相似文献

在这项工作中,我们解决了一杆视觉搜索的对象部分。给定具有注释示能区域的对象的单个参考图像,我们在目标场景内分割出语义对应的部分。我们提出了AffCorrs,这是一种无监督模型,它结合了预训练的DINO-ViT图像描述符和循环对应的属性。我们使用AffCorrs找到相应的启示内和类间的一次性部分分割。这项任务比监督的替代方案更困难,但可以通过模仿和辅助遥操作来学习未来的工作。
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.