Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy
This work addresses the challenge of incremental learning in object detection, a domain-specific problem with incremental improvements over existing replay methods.
The paper tackles the problem of class incremental learning for object detection by introducing an effective buffer training strategy (eBTS) that optimizes replay buffer creation and utilization, achieving state-of-the-art performance on the MS COCO dataset.
Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model This approach has been extensively studied in the context of image classification; however its applicability to object detection is not well established yet. Existing frameworks using replay methods mainly collect replay data without considering the model being trained and tend to rely on randomness or the number of labels of each sample. Also, despite the effectiveness of the replay, it was not yet optimized for the object detection task. In this paper, we introduce an effective buffer training strategy (eBTS) that creates the optimized replay buffer on object detection. Our approach incorporates guarantee minimum and hierarchical sampling to establish the buffer customized to the trained model. %These methods can facilitate effective retrieval of prior knowledge. Furthermore, we use the circular experience replay training to optimally utilize the accumulated buffer data. Experiments on the MS COCO dataset demonstrate that our eBTS achieves state-of-the-art performance compared to the existing replay schemes.