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

Source: [nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection](<https://www.sota2.com/research/paper/68fa6d6a1e209131cea39ac4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:33:23.458Z

Authors: Jinxiang Lai, Wenlong Liu, Jun Liu

Published: 2022-09-08T06:59:42.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.03603>)

[PDF](<https://arxiv.org/pdf/2209.03603.pdf>)