Active Label Refinement for Semantic Segmentation of Satellite Images

by   Tuan Pham Minh, et al.
Universität Kassel

Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.


page 1

page 2

page 3


Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images

Remote sensing data is crucial for applications ranging from monitoring ...

Semantically Informed Multiview Surface Refinement

We present a method to jointly refine the geometry and semantic segmenta...

Semantic Segmentation for Compound figures

Scientific literature contains large volumes of unstructured data,with o...

Towards Global-Scale Crowd+AI Techniques to Map and Assess Sidewalks for People with Disabilities

There is a lack of data on the location, condition, and accessibility of...

A Classification Refinement Strategy for Semantic Segmentation

Based on the observation that semantic segmentation errors are partially...

Please sign up or login with your details

Forgot password? Click here to reset