Open-World Semantic Segmentation Including Class Similarity

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sodano, Matteo, Magistri, Federico, Nunes, Lucas, Behley, Jens, Stachniss, Cyrill
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916156950970368
author Sodano, Matteo
Magistri, Federico
Nunes, Lucas
Behley, Jens
Stachniss, Cyrill
author_facet Sodano, Matteo
Magistri, Federico
Nunes, Lucas
Behley, Jens
Stachniss, Cyrill
contents Interpreting camera data is key for autonomously acting systems, such as autonomous vehicles. Vision systems that operate in real-world environments must be able to understand their surroundings and need the ability to deal with novel situations. This paper tackles open-world semantic segmentation, i.e., the variant of interpreting image data in which objects occur that have not been seen during training. We propose a novel approach that performs accurate closed-world semantic segmentation and, at the same time, can identify new categories without requiring any additional training data. Our approach additionally provides a similarity measure for every newly discovered class in an image to a known category, which can be useful information in downstream tasks such as planning or mapping. Through extensive experiments, we show that our model achieves state-of-the-art results on classes known from training data as well as for anomaly segmentation and can distinguish between different unknown classes.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07532
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open-World Semantic Segmentation Including Class Similarity
Sodano, Matteo
Magistri, Federico
Nunes, Lucas
Behley, Jens
Stachniss, Cyrill
Computer Vision and Pattern Recognition
Interpreting camera data is key for autonomously acting systems, such as autonomous vehicles. Vision systems that operate in real-world environments must be able to understand their surroundings and need the ability to deal with novel situations. This paper tackles open-world semantic segmentation, i.e., the variant of interpreting image data in which objects occur that have not been seen during training. We propose a novel approach that performs accurate closed-world semantic segmentation and, at the same time, can identify new categories without requiring any additional training data. Our approach additionally provides a similarity measure for every newly discovered class in an image to a known category, which can be useful information in downstream tasks such as planning or mapping. Through extensive experiments, we show that our model achieves state-of-the-art results on classes known from training data as well as for anomaly segmentation and can distinguish between different unknown classes.
title Open-World Semantic Segmentation Including Class Similarity
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.07532