Online Learning via Memory: Retrieval-Augmented Detector Adaptation
Abstract
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.
Cite
Text
Jian et al. "Online Learning via Memory: Retrieval-Augmented Detector Adaptation." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91578-9_19Markdown
[Jian et al. "Online Learning via Memory: Retrieval-Augmented Detector Adaptation." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/jian2024eccvw-online/) doi:10.1007/978-3-031-91578-9_19BibTeX
@inproceedings{jian2024eccvw-online,
title = {{Online Learning via Memory: Retrieval-Augmented Detector Adaptation}},
author = {Jian, Yanan and Yu, Fuxun and Zhang, Qi and Levine, William and Dubbs, Brandon and Karianakis, Nikolaos},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {256-265},
doi = {10.1007/978-3-031-91578-9_19},
url = {https://mlanthology.org/eccvw/2024/jian2024eccvw-online/}
}