English

Incremental Few-Shot Object Detection for Robotics

Computer Vision and Pattern Recognition 2022-03-24 v2

Abstract

Incremental few-shot learning is highly expected for practical robotics applications. On one hand, robot is desired to learn new tasks quickly and flexibly using only few annotated training samples; on the other hand, such new additional tasks should be learned in a continuous and incremental manner without forgetting the previous learned knowledge dramatically. In this work, we propose a novel Class-Incremental Few-Shot Object Detection (CI-FSOD) framework that enables deep object detection network to perform effective continual learning from just few-shot samples without re-accessing the previous training data. We achieve this by equipping the widely-used Faster-RCNN detector with three elegant components. Firstly, to best preserve performance on the pre-trained base classes, we propose a novel Dual-Embedding-Space (DES) architecture which decouples the representation learning of base and novel categories into different spaces. Secondly, to mitigate the catastrophic forgetting on the accumulated novel classes, we propose a Sequential Model Fusion (SMF) method, which is able to achieve long-term memory without additional storage cost. Thirdly, to promote inter-task class separation in feature space, we propose a novel regularization technique that extends the classification boundary further away from the previous classes to avoid misclassification. Overall, our framework is simple yet effective and outperforms the previous SOTA with a significant margin of 2.4 points in AP performance.

Keywords

Cite

@article{arxiv.2005.02641,
  title  = {Incremental Few-Shot Object Detection for Robotics},
  author = {Yiting Li and Haiyue Zhu and Sichao Tian and Fan Feng and Jun Ma and Chek Sing Teo and Cheng Xiang and Prahlad Vadakkepat and Tong Heng Lee},
  journal= {arXiv preprint arXiv:2005.02641},
  year   = {2022}
}

Comments

ICRA 2022

R2 v1 2026-06-23T15:20:38.215Z