Incremental Few-Shot Object Detection for Robotics

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.

Authors

• Yiting Li
• Haiyue Zhu
• Sichao Tian
• Fan Feng
• Jun Ma 0008
• Chek Sing Teo
• Cheng Xiang 0001
• Prahlad Vadakkepat
• Tong Heng Lee

Keywords

• Training
• Representation learning
• Performance evaluation
• Degradation
• Image edge detection
• Training data
• Object detection
• Few-shot Object Detection
• Long-term Memory
• Incremental Learning
• Base Classes
• Continuous Manner
• Few-shot Learning
• Sequential Fusion
• Catastrophic Forgetting
• Training Set
• Local Minima
• Raw Images
• Detection Model
• Detection Task
• Weight Vector
• Latent Space
• Training Epochs
• Learning Phase
• Previous Tasks
• Edge Devices
• Sequential Manner
• Incremental Steps
• Box Regression
• Current Task
• Basic Detection
• Phase Increment
• Class Weights
• Balanced Training Set