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.

翻译：类别增量学习旨在解决在持续向已有模型添加未见类别实例时出现的问题。该方法已在图像分类领域得到广泛研究，但其在目标检测中的适用性尚未充分建立。现有采用重放方法的框架主要收集重放数据，而未考虑所训练的模型，往往依赖于随机性或每个样本的标签数量。此外，尽管重放方法有效，但其尚未针对目标检测任务进行优化。本文提出一种高效的缓冲训练策略（eBTS），用于在目标检测中创建优化的重放缓冲区。我们的方法引入了保证最小采样与层次采样，以建立针对所训练模型定制的缓冲区。这些方法能够有效促进先前知识的检索。此外，我们采用循环经验重放训练来最优利用累积的缓冲区数据。在MS COCO数据集上的实验表明，与现有重放方案相比，我们的eBTS达到了最先进的性能。