Panoptic Segmentation of Galactic Structures in LSB Images
This work addresses a domain-specific challenge in astronomy by enhancing the accuracy of galactic structure segmentation in LSB images, which is incremental as it builds on existing segmentation methods.
The paper tackles the problem of localizing galactic structures in low surface brightness (LSB) images, which are often confused with dust contaminants, by proposing a novel unified panoptic segmentation model that combines Mask R-CNN with a contaminant-specialized network and adaptive preprocessing, resulting in greatly improved detection of both structures and contaminants.
We explore the use of deep learning to localise galactic structures in low surface brightness (LSB) images. LSB imaging reveals many interesting structures, though these are frequently confused with galactic dust contamination, due to a strong local visual similarity. We propose a novel unified approach to multi-class segmentation of galactic structures and of extended amorphous image contaminants. Our panoptic segmentation model combines Mask R-CNN with a contaminant specialised network and utilises an adaptive preprocessing layer to better capture the subtle features of LSB images. Further, a human-in-the-loop training scheme is employed to augment ground truth labels. These different approaches are evaluated in turn, and together greatly improve the detection of both galactic structures and contaminants in LSB images.