AI RESEARCH

From Decoupled to Coupled: Robustness Verification for Learning-based Keypoint Detection with Joint Specifications

arXiv CS.LG

ArXi:2603.05604v1 Announce Type: cross Keypoint detection underpins many vision tasks, including pose estimation, viewpoint recovery, and 3D reconstruction, yet modern neural models remain vulnerable to small input perturbations. Despite its importance, formal robustness verification for keypoint detectors is largely unexplored due to high-dimensional inputs and continuous coordinate outputs.