Unsupervised Feature Learning in Remote Sensing
This addresses the practical obstacle of data labeling for deploying deep learning in remote sensing, but it is incremental as it applies an existing method to a new domain.
The paper tackled the problem of needing labeled data for deep learning by applying an unsupervised learning algorithm to the noisy and imbalanced xView dataset, resulting in a feature extractor that adapts to tasks like visual similarity search, outlier identification, and automatic class hierarchy learning, with performance improvements on both common and rare classes.
The need for labeled data is among the most common and well-known practical obstacles to deploying deep learning algorithms to solve real-world problems. The current generation of learning algorithms requires a large volume of data labeled according to a static and pre-defined schema. Conversely, humans can quickly learn generalizations based on large quantities of unlabeled data, and turn these generalizations into classifications using spontaneous labels, often including labels not seen before. We apply a state-of-the-art unsupervised learning algorithm to the noisy and extremely imbalanced xView data set to train a feature extractor that adapts to several tasks: visual similarity search that performs well on both common and rare classes; identifying outliers within a labeled data set; and learning a natural class hierarchy automatically.