论文标题
SID：通过选择性和相关蒸馏的无锚对象检测的增量学习
SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation
论文作者
论文摘要
增量学习需要一个模型才能不断从流数据中学习新任务。但是，在新任务上对训练有素的深度神经网络的传统微调会在旧任务上极大地降低表现 - 这个问题称为灾难性遗忘。在本文中，我们在无锚对象检测的背景下解决了这个问题，这是计算机视觉的新趋势，因为它简单，快速和灵活。由于缺乏对特定模型结构的考虑，因此仅适应当前的增量学习策略在这些无锚点的探测器上失败。为了应对无锚对象检测器上的增量学习的挑战，我们提出了一种新型的增量学习范式，称为选择性和相关蒸馏（SID）。此外，提出了一种新的评估指标，以更好地评估在增量学习条件下检测器的性能。通过在适当的位置进行选择性蒸馏并进一步传输其他实例关系知识，我们的方法在基准数据集Pascal VOC和Coco上显示出显着的优势。
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a problem known as catastrophic forgetting. In this paper, we address this issue in the context of anchor-free object detection, which is a new trend in computer vision as it is simple, fast, and flexible. Simply adapting current incremental learning strategies fails on these anchor-free detectors due to lack of consideration of their specific model structures. To deal with the challenges of incremental learning on anchor-free object detectors, we propose a novel incremental learning paradigm called Selective and Inter-related Distillation (SID). In addition, a novel evaluation metric is proposed to better assess the performance of detectors under incremental learning conditions. By selective distilling at the proper locations and further transferring additional instance relation knowledge, our method demonstrates significant advantages on the benchmark datasets PASCAL VOC and COCO.
