Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jian, Yanan, Yu, Fuxun, Zhang, Qi, Levine, William, Dubbs, Brandon, Karianakis, Nikolaos
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.10716
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916397147226112
author Jian, Yanan
Yu, Fuxun
Zhang, Qi
Levine, William
Dubbs, Brandon
Karianakis, Nikolaos
author_facet Jian, Yanan
Yu, Fuxun
Zhang, Qi
Levine, William
Dubbs, Brandon
Karianakis, Nikolaos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_10716
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online Learning via Memory: Retrieval-Augmented Detector Adaptation
Jian, Yanan
Yu, Fuxun
Zhang, Qi
Levine, William
Dubbs, Brandon
Karianakis, Nikolaos
Computer Vision and Pattern Recognition
Information Retrieval
Machine Learning
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.
title Online Learning via Memory: Retrieval-Augmented Detector Adaptation
topic Computer Vision and Pattern Recognition
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2409.10716