Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rely on the availability of abundant training samples per novel class that substantially limits the scalability to real-world setting where novel data can be scarce. In this paper, we propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision from additional object proposals generated using Selective Search as pseudo labels. We further introduce an incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without forgetting the base classes. Extensive experiments conducted on standard incremental object detection and incremental few-shot object detection settings show that our approach significantly outperforms state-of-the-art methods by a large margin.

翻译：增量式少样本目标检测旨在仅使用少量新颖类别的标注训练数据，在检测新类别时不遗忘基类知识。现有的大多数相关研究依赖于每个新类别拥有充足训练样本的增量式目标检测方法，这严重限制了其在真实场景中（新数据可能稀缺）的可扩展性。本文提出增量式DETR（Incremental-DETR），通过对DETR目标检测器进行微调和自监督学习，实现增量式少样本目标检测。为缓解少量新类别数据导致的严重过拟合问题，我们首先利用选择性搜索（Selective Search）生成的额外目标候选作为伪标签，对DETR的类别特定组件进行自监督微调。此外，我们引入一种结合知识蒸馏的增量式少样本微调策略，对DETR的类别特定组件进行优化，使网络既能检测新类别，又不遗忘基类知识。在标准增量式目标检测和增量式少样本目标检测设定下的大量实验表明，我们的方法以显著优势超越了现有最先进方法。