One-Shot Transfer of Affordance Regions? AffCorrs!

Autor:	Hadjivelichkov, Denis, Zwane, Sicelukwanda, Deisenroth, Marc Peter, Agapito, Lourdes, Kanoulas, Dimitrios
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	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. Comment: Published in Conference on Robot Learning, 2022 For code and dataset, refer to https://sites.google.com/view/affcorrs
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2209.07147 Zobrazit plný text záznamu View this record from Arxiv