Weakly Labeling the Antarctic: The Penguin Colony Case
This work addresses the challenge of ecological monitoring in Antarctica for researchers, though it is incremental as it builds on existing weakly-supervised methods.
The paper tackles the problem of semantic segmentation of Adélie penguin colonies in satellite imagery using a weakly-supervised framework to address scarce pixel-level annotations, resulting in an increase in mean Intersection-over-Union from 42.3% to 60.0%.
Antarctic penguins are important ecological indicators -- especially in the face of climate change. In this work, we present a deep learning based model for semantic segmentation of Adélie penguin colonies in high-resolution satellite imagery. To train our segmentation models, we take advantage of the Penguin Colony Dataset: a unique dataset with 2044 georeferenced cropped images from 193 Adélie penguin colonies in Antarctica. In the face of a scarcity of pixel-level annotation masks, we propose a weakly-supervised framework to effectively learn a segmentation model from weak labels. We use a classification network to filter out data unsuitable for the segmentation network. This segmentation network is trained with a specific loss function, based on the average activation, to effectively learn from the data with the weakly-annotated labels. Our experiments show that adding weakly-annotated training examples significantly improves segmentation performance, increasing the mean Intersection-over-Union from 42.3 to 60.0% on the Penguin Colony Dataset.