nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection
It addresses the problem of adapting object detection models to new environments incrementally, with competitive results in a specific challenge.
The paper tackles continual object detection by proposing nVFNet-RDC, which combines teacher-student models with replay and feature distillation, achieving 55.94% and 54.65% average mAP on two challenge tracks.
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.