Unsupervised Annotation and Detection of Novel Objects Using Known Objectness

Harsh Jadon, Jagdish Deshmukh, Kamakshya Nayak, Kamalakar Thakare, Debi Prosad Dograψ

2024

Abstract

The paper proposes a new approach to detecting and annotating novel objects in images that are not precisely part of a training dataset. The ability to detect novel objects is essential in computer vision, enabling machines to recognise objects that have not been seen before. Current models often fail to detect novel objects as they rely on predefined categories in the training data. Our approach overcomes this limitation by leveraging a large and diverse dataset of objects obtained through web scraping. We extract features using a backbone network and perform clustering to remove redundant data. The resulting dataset is used to retrain the object detection models to obtain results. The method provides deep insights into the effect of clustering and data redundancy removal on performance. Overall, the work contributes to the field of object detection by providing a new approach for detecting novel objects. The method has the potential to be applied to a variety of real-world CV applications.

Paper Citation

in Harvard Style

Jadon H., Deshmukh J., Nayak K., Thakare K. and Prosad Dograψ D. (2024). Unsupervised Annotation and Detection of Novel Objects Using Known Objectness. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 694-701. DOI: 10.5220/0012412400003660

in Bibtex Style

@conference{visapp24,
author={Harsh Jadon and Jagdish Deshmukh and Kamakshya Nayak and Kamalakar Thakare and Debi Prosad Dograψ},
title={Unsupervised Annotation and Detection of Novel Objects Using Known Objectness},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={694-701},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012412400003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Unsupervised Annotation and Detection of Novel Objects Using Known Objectness
SN - 978-989-758-679-8
AU - Jadon H.
AU - Deshmukh J.
AU - Nayak K.
AU - Thakare K.
AU - Prosad Dograψ D.
PY - 2024
SP - 694
EP - 701
DO - 10.5220/0012412400003660
PB - SciTePress