论文标题
NVFNET-RDC：持续对象检测的重播和非本地蒸馏协作
nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection
论文作者
论文摘要
持续学习（CL）的重点是开发具有适应新环境并学习新技能的算法。近年来，这项非常具有挑战性的任务引起了很大的兴趣，新解决方案迅速出现。在本文中，我们提出了一种NVFNET-RDC方法进行连续对象检测。我们的NVFNET-RDC由教师学生组成，并采用重播和功能蒸馏策略。作为第一位解决方案，我们分别在第三个Clvision Challenge Track 2和Track 3上获得了55.94％和54.65％的平均地图。
Continual Learning (CL) focuses on developing algorithms with the ability to adapt to new environments and learn new skills. This very challenging task has generated a lot of interest in recent years, with new solutions appearing rapidly. In this paper, we propose a nVFNet-RDC approach for continual object detection. Our nVFNet-RDC consists of teacher-student models, and adopts replay and feature distillation strategies. As the 1st place solutions, we achieve 55.94% and 54.65% average mAP on the 3rd CLVision Challenge Track 2 and Track 3, respectively.
