Recently few-shot object detection is widely adopted to deal with
data-limited situations. While most previous works merely focus on the
performance on few-shot categories, we claim that detecting all classes is
crucial as test samples may contain any instances in realistic applications,
which requires the few-shot detector to learn new concepts without forgetting.
Through analysis on transfer learning based methods, some neglected but
beneficial properties are utilized to design a simple yet effective few-shot
detector, Retentive R-CNN. It consists of Bias-Balanced RPN to debias the
pretrained RPN and Re-detector to find few-shot class objects without
forgetting previous knowledge. Extensive experiments on few-shot detection
benchmarks show that Retentive R-CNN significantly outperforms state-of-the-art
methods on overall performance among all settings as it can achieve competitive
results on few-shot classes and does not degrade the base class performance at
all. Our approach has demonstrated that the long desired never-forgetting
learner is available in object detection.

本文提出 Retentive R-CNN 模型，通过应用传输学习的一些被忽略的优良属性，使用 Bias-Balanced RPN 去除预训练误差和 Re-detector 找出 few-shot 类物体并避免遗忘前面的知识，来实现 few-shot 目标检测任务中的长期记忆。实验表明，Retentive R-CNN 在各种设置下均可实现对 few-shot 类别的有竞争力的结果，而且不会降低基类的性能。