English

Online Learning via Memory: Retrieval-Augmented Detector Adaptation

Computer Vision and Pattern Recognition 2024-09-18 v1 Information Retrieval Machine Learning

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.

Keywords

Cite

@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

R2 v1 2026-06-28T18:46:54.912Z