This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.
@article{arxiv.2409.10716,
title = {Online Learning via Memory: Retrieval-Augmented Detector Adaptation},
author = {Yanan Jian and Fuxun Yu and Qi Zhang and William Levine and Brandon Dubbs and Nikolaos Karianakis},
journal= {arXiv preprint arXiv:2409.10716},
year = {2024}
}
Comments
Accepted at ECCV 2024, Human-Inspired Computer Vision (HCV) workshop