增强框重放：克服增量目标检测中的前景偏移问题
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection
AI总结：
针对增量目标检测中图像重放存在的前景偏移问题，提出仅存储重放前景对象的ABR方法及注意力RoI蒸馏损失，在降低遗忘、保持可塑性的同时减少存储需求，实现了SOTA性能。
摘要：
在增量学习中，重放先前任务的存储样本与当前任务样本是解决灾难性遗忘的最高效方法之一。然而，与增量分类不同，图像重放尚未成功应用于增量目标检测（IOD）。本文中，我们指出被忽视的前景偏移问题是导致这一现象的主要原因。前景偏移仅在重放先前任务的图像时发生，指的是这些图像的背景中可能包含当前任务的前景对象这一情况。为解决该问题，我们提出了一种新颖高效的增强框重放（Augmented Box Replay, ABR）方法，该方法仅存储和重放前景对象，从而规避前景偏移问题。此外，我们提出了一种创新的注意力感兴趣区域蒸馏（Attentive RoI Distillation）损失，利用感兴趣区域（RoI）特征的空间注意力约束当前模型聚焦于旧模型的最重要信息。ABR 显著降低了对先前类别的遗忘，同时保持了对当前类别的高可塑性。此外，与标准图像重放相比，它大幅降低了存储需求。在 Pascal-VOC 和 COCO 数据集上的综合实验验证了我们模型的最优性能。
英文摘要：
In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
