Back to Search
Start Over
Meta-Learning-Based Incremental Few-Shot Object Detection.
- Source :
- IEEE Transactions on Circuits & Systems for Video Technology; May2022, Vol. 71 Issue 5, p2158-2169, 12p
- Publication Year :
- 2022
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- OBJECT recognition (Computer vision)
MACHINE learning
FEATURE extraction
DETECTORS
Subjects
Details
- Language :
- English
- ISSN :
- 10518215
- Volume :
- 71
- Issue :
- 5
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Circuits & Systems for Video Technology
- Publication Type :
- Academic Journal
- Accession number :
- 156273066
- Full Text :
- https://doi.org/10.1109/TCSVT.2021.3088545