Language-Driven Active Learning for Diverse Open-Set 3D Object Detection

arXiv:2404.12856v1 Announce Type: cross
Abstract: Object detection is crucial for ensuring safe autonomous driving. However, data-driven approaches face challenges when encountering minority or novel objects in the 3D driving scene. In this paper, we propose VisLED, a language-driven active learning framework for diverse open-set 3D Object Detection. Our method leverages active learning techniques to query diverse and informative data samples from an unlabeled pool, enhancing the model's ability to detect underrepresented or novel objects. Specifically, we introduce the Vision-Language Embedding …

3d object 3d object detection abstract active learning arxiv autonomous autonomous driving challenges cs.ai cs.cv cs.lg data data-driven detection diverse driving face framework however language novel object objects paper safe set type