Multi-modal generalized class discovery for scalable autonomous all-sky surveys
Presenter: Laura Domine
Title: Multi-modal generalized class discovery for scalable autonomous all-sky surveys
Date/Time: Friday, June 21st, 1:30 - 2:00 PM
Abstract: The Galileo Project is a systematic scientific research program focused on understanding the origins and nature of Unidentified Aerial Phenomena (UAP). To date there is very little data on UAP whose properties and kinematics purportedly reside outside the performance envelope of known phenomena. We are in the process of designing, building and commissioning a multi-modal, multi-spectral detector to continuously monitor the sky and collect UAP data through a rigorous aerial census of natural and human-made phenomena. This open-world setting is a major challenge for artificial intelligence (AI) techniques which need to both (i) accurately detect and classify objects from known classes and (ii) cluster unknown, out-of-distribution objects. Using a mix of simulated and commissioning dataset, which includes several months of videos from an all-sky array of eight near-infrared cameras and audible recordings, I will discuss our work developing a multi-modal generalized class discovery method to automatically identify new classes of objects in unlabeled data in addition to known classes. It opens the door to an autonomous aerial census where categorization relies less on our prior expectations.