# Online Learning via Memory: Retrieval-Augmented Detector Adaptation

Source: [Online Learning via Memory: Retrieval-Augmented Detector Adaptation](<https://www.sota2.com/research/paper/68fa74e01e209131cea645d3>)

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

Data updated: 2025-10-26T03:20:26.911Z

Authors: Yanan Jian, Fuxun Yu, Qi Zhang, William Levine, Brandon Dubbs, Nikolaos Karianakis

Published: 2024-09-16T20:40:26.000Z

## 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.

## 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/2409.10716>)

[PDF](<https://arxiv.org/pdf/2409.10716.pdf>)
