RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shor, Tamir, Leifman, George, Beryozkin, Genady
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915929585090560
author Shor, Tamir
Leifman, George
Beryozkin, Genady
author_facet Shor, Tamir
Leifman, George
Beryozkin, Genady
contents Object-Counting for remote-sensing (RS) imagery is attracting increasing research interest due to its crucial role in a wide and diverse set of applications. While several promising methods for RS object-counting have been proposed, existing methods focus on a closed, pre-defined set of object classes. This limitation necessitates costly re-annotation and model re-training to adapt current approaches for counting of novel objects that have not been seen during training, and severely inhibits their application in dynamic, real-world monitoring scenarios. To address this gap, in this work we propose RS-OVC - the first Open Vocabulary Counting (OVC) model for Remote-Sensing and aerial imagery. We show that our model is capable of accurate counting of novel object classes, that were unseen during training, based solely on textual and/or visual conditioning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08704
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data
Shor, Tamir
Leifman, George
Beryozkin, Genady
Computer Vision and Pattern Recognition
Object-Counting for remote-sensing (RS) imagery is attracting increasing research interest due to its crucial role in a wide and diverse set of applications. While several promising methods for RS object-counting have been proposed, existing methods focus on a closed, pre-defined set of object classes. This limitation necessitates costly re-annotation and model re-training to adapt current approaches for counting of novel objects that have not been seen during training, and severely inhibits their application in dynamic, real-world monitoring scenarios. To address this gap, in this work we propose RS-OVC - the first Open Vocabulary Counting (OVC) model for Remote-Sensing and aerial imagery. We show that our model is capable of accurate counting of novel object classes, that were unseen during training, based solely on textual and/or visual conditioning.
title RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.08704