paper-with-me

홈 › Papers

Online Learning via Memory: Retrieval-Augmented Detector Adaptation

2024-09-16 · Yanan Jian, Fuxun Yu, Qi Zhang, William LeVine, Brandon Dubbs, Nikolaos Karianakis

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.

📄 PDF Abstract BibTeX arXiv:2409.10716

Code (0)

등록된 구현이 없습니다.

Tasks

Memorizationobject-detectionObject DetectionRetrieval

Similar Papers 제목 키워드 기반

Retrieval-Augmented Memory for Online Learning

2025-12-02 · Wenzhang Du arxiv

Retrieval-augmented models couple parametric predictors with non-parametric memories, but their use in streaming supervised learning with concept drift is not well understood. We study online classification in non-statio…

DMA: Online RAG Alignment with Human Feedback

2025-11-06 · Yu Bai, Yukai Miao, Dawei Wang, Li Chen 외 arxiv

Retrieval-augmented generation (RAG) systems often rely on static retrieval, limiting adaptation to evolving intent and content drift. We introduce Dynamic Memory Alignment (DMA), an online learning framework that system…

Knowledge Distillation

SOMA: Strategic Orchestration and Memory-Augmented System for Vision-Language-Action Model Robustness via In-Context Adaptation

2026-03-25 · Zhuoran Li, Zhiyang Li, Kaijun Zhou, Jinyu Gu arxiv

Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentall…

Online Adaptation of Language Models with a Memory of Amortized Contexts

2024-03-07 · Jihoon Tack, Jaehyung Kim, Eric Mitchell, Jinwoo Shin 외

Due to the rapid generation and dissemination of information, large language models (LLMs) quickly run out of date despite enormous development costs. To address the crucial need to keep models updated, online learning h…

Language ModellingMeta-Learning

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents

2026-05-05 · Ishrith Gowda arxiv

Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We formalize memory poisoning attacks on retrieval-augmented agents as a Sta…

Anomaly Detection