Open-world (OW) recognition and detection models show strong zero- and few-shot adaptation abilities, inspiring their use as initializations in continual learning methods to improve performance. Despite promising results on seen classes, such OW abilities on unseen classes are largely degenerated due to catastrophic forgetting. To tackle this challenge, we propose an open-world continual object detection task, requiring detectors to generalize to old, new, and unseen categories in continual learning scenarios. Based on this task, we present a challenging yet practical OW-COD benchmark to assess detection abilities. The goal is to motivate OW detectors to simultaneously preserve learned classes, adapt to new classes, and maintain open-world capabilities under few-shot adaptations. To mitigate forgetting in unseen categories, we propose MR-GDINO, a strong, efficient and scalable baseline via memory and retrieval mechanisms within a highly scalable memory pool. Experimental results show that existing continual detectors suffer from severe forgetting for both seen and unseen categories. In contrast, MR-GDINO largely mitigates forgetting with only 0.1% activated extra parameters, achieving state-of-the-art performance for old, new, and unseen categories.

翻译：开放世界（OW）识别与检测模型展现出强大的零样本与少样本适应能力，这启发了将其作为持续学习方法中的初始化模型以提升性能。尽管在已见类别上取得了有希望的结果，但由于灾难性遗忘，此类模型在未见类别上的开放世界能力大幅退化。为应对这一挑战，我们提出了一项开放世界持续目标检测任务，要求检测器在持续学习场景中能够泛化至旧类别、新类别及未见类别。基于此任务，我们提出了一个具有挑战性且实用的OW-COD基准来评估检测能力。其目标是激励开放世界检测器在少样本适应下，同时保持已学类别、适应新类别并维持开放世界能力。为减轻未见类别的遗忘，我们提出了MR-GDINO，这是一个通过高度可扩展的记忆池内的记忆与检索机制实现的强大、高效且可扩展的基线方法。实验结果表明，现有的持续检测器在已见和未见类别上均遭受严重的遗忘。相比之下，MR-GDINO仅激活0.1%的额外参数即大幅减轻了遗忘，并在旧类别、新类别及未见类别上实现了最先进的性能。