Novel-Registrable Weights and Region-Level Contrastive Learning for Incremental Few-shot Object Detection

Shiyuan Tang, Hefei Mei, Heqian Qiu, Xinpeng Hao, Taijin Zhao, Benliu Qiu, Haoyang Cheng, Jian Jiao, Chuanyang Gong, Hongliang Li

Abstract: Few-shot object detection (FSOD) methods learn to detect novel objects from a few data, which also requires reusing base class data if detecting base objects is necessary. However, in some real applications, it is difficult to obtain old class data due to privacy or limited storage capacity, causing catastrophic forgetting when learning new classes. Therefore, incremental few-shot object detection (iFSOD) has attracted the attention of researchers in recent years. The iFSOD methods continuously learn novel classes and not forget learned knowledge without storing old class data. In this paper, we propose a novel method using novel-registrable weights and region-level contrastive learning (NWRC) for iFSOD. First, we use novel-registrable weights for RoI classification, which memorizes class-specific weights to alleviate forgetting old knowledge and registers new weights for novel classes. Then we propose region-level contrastive learning in the base training stage by proposal box augmentation, enhancing the generalizability of the feature representations and plasticity of the detector. We verify the effectiveness of our method on two experimental settings of iFSOD on COCO and VOC datasets. The results show that our method has the ability to learn novel classes with a few-shot dataset and not forget old classes.