AI RESEARCH
Deploy DINO with Many-to-Many Association
arXiv CS.CV
•
ArXi:2604.23670v1 Announce Type: new Motivated by the limited generalization of supervised image matching models to unseen image domains, we explore the zero-shot deployment of DINO features for this task. The generalist visual representation extracted from DINO has inherent ambiguity when used to match feature points among semantically similar instances, prompting us to adopt a many-to-many (m-to-m) matching paradigm.