Aerial image segmentation with minimal annotation effort using clustering of pretrained embeddings

Sabina van Rooij; Maarten C. Kruithof; Wyke Huizinga; Gertjan Burghouts; Klamer Schutte

doi:10.1117/12.2688450

17 October 2023 Aerial image segmentation with minimal annotation effort using clustering of pretrained embeddings

Sabina van Rooij, Maarten C. Kruithof, Wyke Huizinga, Gertjan Burghouts, Klamer Schutte

Proceedings Volume 12742, Artificial Intelligence for Security and Defence Applications; 127420M (2023) https://doi.org/10.1117/12.2688450
Event: SPIE Security + Defence, 2023, Amsterdam, Netherlands

Abstract

antic segmentation of aerial images is a critical task in various domains such as urban planning, and monitoring deforestation or critical infrastructure. However, the annotation process required for training accurate segmentation models is often time-consuming and labor-intensive. This paper presents a novel approach to address this challenge by leveraging the power of clustering techniques applied to the embeddings obtained from a SimCLRv2 model pretrained on the ImageNet dataset. By using this clustering approach, fewer training samples are needed, and the annotation only needs to be done for each cluster instead of each pixel in the image, significantly reducing the annotation time. Our proposed method uses SimCLRv2 to obtain rich feature representations (embeddings) from a dataset of unlabeled aerial images. These embeddings are then subjected to clustering, enabling the grouping of semantically similar image regions. In addition to directly using these clusters as class labels, we can treat these clusters as pseudo-classes, allowing us to construct a pseudo-label dataset for fine-tuning a segmentation network. Through experiments conducted on two benchmark aerial image datasets (Potsdam and Vaihingen), we demonstrate the effectiveness of our approach in achieving segmentation results in line with similar works on few-shot segmentation while significantly reducing the annotation effort required, thereby highlighting its practical applicability. Overall, the combination of SimCLRv2 embeddings and clustering techniques presents a promising avenue for achieving accurate image segmentation while minimizing the annotation burden, making it highly relevant for remote sensing applications and aerial imagery analysis.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Sabina van Rooij, Maarten C. Kruithof, Wyke Huizinga, Gertjan Burghouts, and Klamer Schutte "Aerial image segmentation with minimal annotation effort using clustering of pretrained embeddings", Proc. SPIE 12742, Artificial Intelligence for Security and Defence Applications, 127420M (17 October 2023); https://doi.org/10.1117/12.2688450

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available