# Incremental Few-Shot Object Detection for Robotics

arXiv: https://arxiv.org/abs/2005.02641 · HTML: https://mlsanity.com/paper/2005.02641/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2020.

## Built on by (most cited first, 5 of 5)

- [Detect Everything with Few Examples](https://mlsanity.com/paper/2309.12969/) (2023)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention](https://mlsanity.com/paper/2302.10501/) (2023)
- [A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space](https://mlsanity.com/paper/2412.14680/) (2024)
- [Multi-Frequency-Aware Patch Adversarial Learning for Neural Point Cloud Rendering](https://mlsanity.com/paper/2210.03693/) (2022)

## Abstract (arXiv)

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.