Popeye: A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery

arXiv:2403.03790v1 Announce Type: new
Abstract: Ship detection needs to identify ship locations from remote sensing (RS) scenes. However, due to different imaging payloads, various appearances of ships, and complicated background interference from the bird's eye view, it is difficult to set up a unified paradigm for achieving multi-source ship detection. Therefore, in this article, considering that the large language models (LLMs) emerge the powerful generalization ability, a novel unified visual-language model called Popeye is proposed for multi-source ship detection from …

abstract arxiv bird cs.cv detection however identify imaging interference language language model locations paradigm sensing set ship ships type view visual