Active Label Refinement for Semantic Segmentation of Satellite Images
This addresses the problem of expensive labeling for remote sensing applications, offering a cost-efficient method, though it is incremental as it builds on existing active learning and segmentation techniques.
The paper tackles the high cost of expert labeling for satellite image segmentation by proposing a two-step approach: using low-cost initial labels (e.g., crowdsourcing) and then refining them with active learning, showing benefits in performance on a dataset from Bengaluru, India.
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.