Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gouidis, Filipos, Papoutsakis, Konstantinos, Patkos, Theodore, Argyros, Antonis, Plexousakis, Dimitris
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909649386602496
author Gouidis, Filipos
Papoutsakis, Konstantinos
Patkos, Theodore
Argyros, Antonis
Plexousakis, Dimitris
author_facet Gouidis, Filipos
Papoutsakis, Konstantinos
Patkos, Theodore
Argyros, Antonis
Plexousakis, Dimitris
contents We investigate the problem of Object State Classification (OSC) as a zero-shot learning problem. Specifically, we propose the first Object-agnostic State Classification (OaSC) method that infers the state of a certain object without relying on the knowledge or the estimation of the object class. In that direction, we capitalize on Knowledge Graphs (KGs) for structuring and organizing knowledge, which, in combination with visual information, enable the inference of the states of objects in object/state pairs that have not been encountered in the method's training set. A series of experiments investigate the performance of the proposed method in various settings, against several hypotheses and in comparison with state of the art approaches for object attribute classification. The experimental results demonstrate that the knowledge of an object class is not decisive for the prediction of its state. Moreover, the proposed OaSC method outperforms existing methods in all datasets and benchmarks by a great margin.
format Preprint
id arxiv_https___arxiv_org_abs_2307_12179
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs
Gouidis, Filipos
Papoutsakis, Konstantinos
Patkos, Theodore
Argyros, Antonis
Plexousakis, Dimitris
Computer Vision and Pattern Recognition
We investigate the problem of Object State Classification (OSC) as a zero-shot learning problem. Specifically, we propose the first Object-agnostic State Classification (OaSC) method that infers the state of a certain object without relying on the knowledge or the estimation of the object class. In that direction, we capitalize on Knowledge Graphs (KGs) for structuring and organizing knowledge, which, in combination with visual information, enable the inference of the states of objects in object/state pairs that have not been encountered in the method's training set. A series of experiments investigate the performance of the proposed method in various settings, against several hypotheses and in comparison with state of the art approaches for object attribute classification. The experimental results demonstrate that the knowledge of an object class is not decisive for the prediction of its state. Moreover, the proposed OaSC method outperforms existing methods in all datasets and benchmarks by a great margin.
title Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.12179