{"title":"通过记忆进行在线学习:检索-增强探测器适应性","authors":"Yanan Jian, Fuxun Yu, Qi Zhang, William Levine, Brandon Dubbs, Nikolaos Karianakis","doi":"arxiv-2409.10716","DOIUrl":null,"url":null,"abstract":"This paper presents a novel way of online adapting any off-the-shelf object\ndetection model to a novel domain without retraining the detector model.\nInspired by how humans quickly learn knowledge of a new subject (e.g.,\nmemorization), we allow the detector to look up similar object concepts from\nmemory during test time. This is achieved through a retrieval augmented\nclassification (RAC) module together with a memory bank that can be flexibly\nupdated with new domain knowledge. We experimented with various off-the-shelf\nopen-set detector and close-set detectors. With only a tiny memory bank (e.g.,\n10 images per category) and being training-free, our online learning method\ncould significantly outperform baselines in adapting a detector to novel\ndomains.","PeriodicalId":501281,"journal":{"name":"arXiv - CS - Information Retrieval","volume":"18 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Online Learning via Memory: Retrieval-Augmented Detector Adaptation\",\"authors\":\"Yanan Jian, Fuxun Yu, Qi Zhang, William Levine, Brandon Dubbs, Nikolaos Karianakis\",\"doi\":\"arxiv-2409.10716\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a novel way of online adapting any off-the-shelf object\\ndetection model to a novel domain without retraining the detector model.\\nInspired by how humans quickly learn knowledge of a new subject (e.g.,\\nmemorization), we allow the detector to look up similar object concepts from\\nmemory during test time. This is achieved through a retrieval augmented\\nclassification (RAC) module together with a memory bank that can be flexibly\\nupdated with new domain knowledge. We experimented with various off-the-shelf\\nopen-set detector and close-set detectors. With only a tiny memory bank (e.g.,\\n10 images per category) and being training-free, our online learning method\\ncould significantly outperform baselines in adapting a detector to novel\\ndomains.\",\"PeriodicalId\":501281,\"journal\":{\"name\":\"arXiv - CS - Information Retrieval\",\"volume\":\"18 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Information Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10716\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10716","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Online Learning via Memory: Retrieval-Augmented Detector Adaptation
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.