Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners

arXiv:2404.19696v1 Announce Type: cross
Abstract: 3D visual grounding is a challenging task that often requires direct and dense supervision, notably the semantic label for each object in the scene. In this paper, we instead study the naturally supervised setting that learns from only 3D scene and QA pairs, where prior works underperform. We propose the Language-Regularized Concept Learner (LARC), which uses constraints from language as regularization to significantly improve the accuracy of neuro-symbolic concept learners in the naturally supervised setting. …

abstract arxiv concept cs.ai cs.cl cs.cv cs.lg language object paper prior semantic study supervision type visual