Interactive Learning for Semantic Segmentation in Earth Observation
This addresses the need for more accurate scene understanding in Earth observation, though it is incremental as it builds on existing interactive methods.
The paper tackles the problem of inaccurate semantic segmentation maps in Earth observation by proposing DISCA, an interactive learning framework that refines maps using sparse user annotations, achieving up to 4.7% IoU improvement with ten clicks.
Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation). It consists of continually adapting a neural network to a target image using an interactive learning process with sparse user annotations as ground-truth. We show through experiments on three datasets using synthesized annotations the benefits of the approach, reaching an IoU improvement up to 4.7% for ten sampled clicks. Finally, we exhibit that our approach can be particularly rewarding when it is faced to additional issues such as domain adaptation.