将视觉提示方法用于增量目标检测，发现仅靠提示效果不佳，结合少量旧数据回放才能提升性能。
Incremental Object Detection with Prompt-based Methods
- 用可学习的视觉提示向量实现模型更新，保持主干网络不变
- 纯提示方法在复杂增量场景下性能落后于基线，但提示+小量回放效果最佳
- 为增量目标检测中的提示方法设计提供实证参考，适合关注高效学习的研究者
视觉提示方法在图像分类的增量学习中受到越来越多关注。这类方法通过学习额外的嵌入向量来更新模型，同时冻结主干网络，训练效率高。然而，此前尚无研究将其应用于增量目标检测（IOD），其泛化能力尚不明确。本文在复杂的领域增量学习设置下，分析了三种不同的提示方法，并提供了广泛的基准对比。实验表明，所测试的提示方法在该设置下表现不佳。但一种结合视觉提示与少量历史数据回放的实用方法取得了最优结果。此外，通过提示长度和初始化方式的额外实验，我们的研究为推进提示方法在增量目标检测中的应用提供了重要见解。
原文摘要 · Abstract (English)
Visual prompt-based methods have seen growing interest in incremental learning (IL) for image classification. These approaches learn additional embedding vectors while keeping the model frozen, making them efficient to train. However, no prior work has applied such methods to incremental object detection (IOD), leaving their generalizability unclear. In this paper, we analyze three different prompt-based methods under a complex domain-incremental learning setting. We additionally provide a wide range of reference baselines for comparison. Empirically, we show that the prompt-based approaches we tested underperform in this setting. However, a strong yet practical method, combining visual prompts with replaying a small portion of previous data, achieves the best results. Together with additional experiments on prompt length and initialization, our findings offer valuable insights for advancing prompt-based IL in IOD.
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。