YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery

arXiv:2404.00257v1 Announce Type: cross
Abstract: Because of its use in practice, open-world object detection (OWOD) has gotten a lot of attention recently. The challenge is how can a model detect novel classes and then incrementally learn them without forgetting previously known classes. Previous approaches hinge on strongly-supervised or weakly-supervised novel-class data for novel-class detection, which may not apply to real applications. We construct a new benchmark that novel classes are only encountered at the inference stage. And we propose a …

abstract arxiv attention challenge class cs.ai cs.cv cs.lg detection discovery eess.iv hinge incremental learn novel object open-world practice them type weakly-supervised world yolo