nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

09/08/2022

∙

by   Jinxiang Lai, et al.

∙

4

∙

share

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 3, respectively.