Learning crop type mapping from regional label proportions in large-scale SAR and optical imagery
This addresses the challenge of large-scale image annotation in Earth observation for agricultural monitoring, though it is incremental as it builds on existing contrastive-learning and clustering techniques.
The study tackled the problem of expensive pixel-level annotation in Earth observation by using government crop-proportion data as priors to train a deep clustering method for crop type mapping, achieving higher accuracy for major crop types in Brazilian agricultural regions with synthetic-aperture radar and optical images.
The application of deep learning algorithms to Earth observation (EO) in recent years has enabled substantial progress in fields that rely on remotely sensed data. However, given the data scale in EO, creating large datasets with pixel-level annotations by experts is expensive and highly time-consuming. In this context, priors are seen as an attractive way to alleviate the burden of manual labeling when training deep learning methods for EO. For some applications, those priors are readily available. Motivated by the great success of contrastive-learning methods for self-supervised feature representation learning in many computer-vision tasks, this study proposes an online deep clustering method using crop label proportions as priors to learn a sample-level classifier based on government crop-proportion data for a whole agricultural region. We evaluate the method using two large datasets from two different agricultural regions in Brazil. Extensive experiments demonstrate that the method is robust to different data types (synthetic-aperture radar and optical images), reporting higher accuracy values considering the major crop types in the target regions. Thus, it can alleviate the burden of large-scale image annotation in EO applications.