提出高效持续检测框架MR-GDINO，兼顾旧、新、未见类不遗忘。
MR-GDINO: Efficient Open-World Continual Object Detection
- 用记忆检索机制构建可扩展存储池，实现高效知识保留。
- 仅用0.1%额外参数即显著减少新旧类别遗忘，性能领先。
- 适合需要长期适应新类别且保持泛化能力的实时检测场景。
开放世界（OW）识别与检测模型具备强大的零样本和少样本适应能力，启发将其作为持续学习方法的初始化以提升性能。尽管在已见类别上表现良好，但对未见类别的开放世界能力因灾难性遗忘而大幅退化。为此，我们提出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同时泛化于旧类别、新类别及未见类别。基于此任务，我们构建了一个具有挑战性且实用的OW-COD基准，用于评估检测能力。目标是促使开放世界检测器同时保持已学类别、适应新类别，并在少样本条件下维持开放世界能力。为缓解未见类别遗忘问题，我们提出MR-GDINO，一种强效、高效且可扩展的基线方法，通过内存与检索机制在高度可扩展的记忆池中实现。实验表明，现有持续检测器在已见和未见类别上均出现严重遗忘；而MR-GDINO仅需0.1%激活的额外参数，便大幅缓解遗忘，实现了旧类别、新类别及未见类别上的最先进性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。