Clustering augmented Self-Supervised Learning: Anapplication to Land Cover Mapping

Abstract

Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of addressing this issue, based on the underlying idea of pre-training the Deep Neural Networks (DNN) on freely available large datasets, cannot be used for Remote Sensing due to the unavailability of such large-scale labeled datasets and the heterogeneity of data sources caused by the varying spatial and spectral resolution of different sensors. Self-supervised learning is an alternative approach that learns feature representation from unlabeled images without using any human annotations. In this paper, we introduce a new method for land cover mapping by using a clustering based pretext task for self-supervised learning. We demonstrate the effectiveness of the method on two societally relevant applications from the aspect of segmentation performance, discriminative feature representation learning and the underlying cluster structure. We also show the effectiveness of the active sampling using the clusters obtained from our method in improving the mapping accuracy given a limited budget of annotating.

arXiv comment9 Pages, 7 figures, presented at the DeepSpatial workshop at KDD'21

References in corpus (8)

• Distributed Representations of Words and Phrases and their Compositionality
• Unsupervised Representation Learning by Predicting Image Rotations
• What makes ImageNet good for transfer learning?
• Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping
• Segmentation of Satellite Imagery using U-Net Models for Land Cover Classification
• In-domain representation learning for remote sensing
• Land Cover Change Detection via Semantic Segmentation
• Land Cover Mapping in Limited Labels Scenario: A Survey