BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection

arXiv:2403.02637v1 Announce Type: new
Abstract: Humans can easily distinguish the known and unknown categories and can recognize the unknown object by learning it once instead of repeating it many times without forgetting the learned object. Hence, we aim to make deep learning models simulate the way people learn. We refer to such a learning manner as OnLine Open World Object Detection(OLOWOD). Existing OWOD approaches pay more attention to the identification of unknown categories, while the incremental learning part is also …

abstract aim arxiv brain brain-inspired cs.cv deep learning detection humans learn object people streaming the unknown the way type world