Meta-Learning-Based Incremental Few-Shot Object Detection

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 4; pp. 2158 - 2169
• Main Authors: Cheng, Meng, Wang, Hanli, Long, Yu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Data models; Detectors; Feature extraction; Few-shot learning; incremental learning; Learning; meta-learning; Object detection; Object recognition; Task analysis; Training
• DOI: 10.1109/TCSVT.2021.3088545
• ISSN: 1051-8215

Recent years have witnessed meaningful progress in the task of few-shot object detection. However, most of the existing models are not capable of incremental learning with a few samples, i.e. , the detector can't detect novel-class objects by using only a few samples of novel classes (without revisiting the original training samples) while maintaining the performances on base classes. This is largely because of catastrophic forgetting, which is a general phenomenon in few-shot learning that the incorporation of the unseen information ( e.g. , novel-class objects) will lead to a serious loss of the knowledge learnt before ( e.g. , base-class objects). In this paper, a new model is proposed for incremental few-shot object detection, which takes CenterNet as the fundamental framework and redesigns it by introducing a novel meta-learning method to make the model adapted to unseen knowledge while overcoming forgetting to a great extent. Specifically, a meta-learner is trained with the base-class samples, providing the object locator of the proposed model with a good weight initialization, and thus the proposed model can be fine-tuned easily with few novel-class samples. On the other hand, the filters correlated to base classes are preserved when fine-tuning the proposed model with the few samples of novel classes, which is a simple but effective solution to mitigate the problem of forgetting. The experiments on the benchmark MS COCO and PASCAL VOC datasets demonstrate that the proposed model outperforms the state-of-the-art methods by a large margin in the detection performances on base classes and all classes while achieving best performances when detecting novel-class objects in most cases. The project page can be found in https://mic.tongji.edu.cn/e6/d5/c9778a190165/page.htm .