论文标题
Sylph：一个超级核框架，用于增量几弹对象检测
Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection
论文作者
论文摘要
我们研究了具有挑战性的增量射击对象检测（IFSD）设置。最近，在成功的连续和无芬特IFSD的背景下，已经研究了基于超网络的方法。我们仔细研究了此类方法的重要设计选择，从而导致了一些关键的改进，并导致了更准确，更灵活的框架，我们称之为Sylph。特别是，我们通过利用基本检测器在大规模数据集上鉴定的基本检测器来证明将对象分类与本地化的有效性。与以前的结果提出的相反，我们表明，使用精心设计的类条件超级net工作，无芬特原子IFSD可以非常有效，尤其是当大量具有丰富数据的基本类别可用于元训练时，几乎可以接近经过测试时间训练的替代方案。考虑到它的许多实际优势，该结果更加重要：（1）在没有其他培训的情况下按顺序学习新课程，（2）在单次通过中检测新颖和可见的课程，以及（3）不要忘记先前看到的课程。我们在可可和LVI上基准了我们的模型，在LVIS上的长尾稀有类别上报告了高达17％的AP，这表明基于超网络的IFSD有望。
We study the challenging incremental few-shot object detection (iFSD) setting. Recently, hypernetwork-based approaches have been studied in the context of continuous and finetune-free iFSD with limited success. We take a closer look at important design choices of such methods, leading to several key improvements and resulting in a more accurate and flexible framework, which we call Sylph. In particular, we demonstrate the effectiveness of decoupling object classification from localization by leveraging a base detector that is pretrained for class-agnostic localization on a large-scale dataset. Contrary to what previous results have suggested, we show that with a carefully designed class-conditional hypernetwork, finetune-free iFSD can be highly effective, especially when a large number of base categories with abundant data are available for meta-training, almost approaching alternatives that undergo test-time-training. This result is even more significant considering its many practical advantages: (1) incrementally learning new classes in sequence without additional training, (2) detecting both novel and seen classes in a single pass, and (3) no forgetting of previously seen classes. We benchmark our model on both COCO and LVIS, reporting as high as 17% AP on the long-tail rare classes on LVIS, indicating the promise of hypernetwork-based iFSD.
