Incremental Few-Shot Object Detection for Robotics
| العنوان: | Incremental Few-Shot Object Detection for Robotics |
|---|---|
| المؤلفون: | Yiting Li, Haiyue Zhu, Sichao Tian, Fan Feng, Jun Ma, Chek Sing Teo, Cheng Xiang, Prahlad Vadakkepat, Tong Heng Lee |
| المصدر: | 2022 International Conference on Robotics and Automation (ICRA). |
| بيانات النشر: | IEEE, 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | 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. Comment: ICRA 2022 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b53b499565f1ca91fa753efc837a358e https://doi.org/10.1109/icra46639.2022.9811856 |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....b53b499565f1ca91fa753efc837a358e |
| قاعدة البيانات: | OpenAIRE |
| الوصف غير متاح. |