On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Refael, Yehonathan, Aides, Amit, Barzilai, Aviad, Leifman, George, Beryozkin, Genady, Silverman, Vered, Jaber, Bolous, Shekel, Tomer
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917070228160512
author Refael, Yehonathan
Aides, Amit
Barzilai, Aviad
Leifman, George
Beryozkin, Genady
Silverman, Vered
Jaber, Bolous
Shekel, Tomer
author_facet Refael, Yehonathan
Aides, Amit
Barzilai, Aviad
Leifman, George
Beryozkin, Genady
Silverman, Vered
Jaber, Bolous
Shekel, Tomer
contents Open-vocabulary object detection (OVD) models offer remarkable flexibility by detecting objects from arbitrary text queries. However, their zero-shot performance in specialized domains like Remote Sensing (RS) is often compromised by the inherent ambiguity of natural language, limiting critical downstream applications. For instance, an OVD model may struggle to distinguish between fine-grained classes such as "fishing boat" and "yacht" since their embeddings are similar and often inseparable. This can hamper specific user goals, such as monitoring illegal fishing, by producing irrelevant detections. To address this, we propose a cascaded approach that couples the broad generalization of a large pre-trained OVD model with a lightweight few-shot classifier. Our method first employs the zero-shot model to generate high-recall object proposals. These proposals are then refined for high precision by a compact classifier trained in real-time on only a handful of user-annotated examples - drastically reducing the high costs of RS imagery annotation.The core of our framework is FLAME, a one-step active learning strategy that selects the most informative samples for training. FLAME identifies, on the fly, uncertain marginal candidates near the decision boundary using density estimation, followed by clustering to ensure sample diversity. This efficient sampling technique achieves high accuracy without costly full-model fine-tuning and enables instant adaptation, within less then a minute, which is significantly faster than state-of-the-art alternatives.Our method consistently surpasses state-of-the-art performance on RS benchmarks, establishing a practical and resource-efficient framework for adapting foundation models to specific user needs.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17670
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration
Refael, Yehonathan
Aides, Amit
Barzilai, Aviad
Leifman, George
Beryozkin, Genady
Silverman, Vered
Jaber, Bolous
Shekel, Tomer
Machine Learning
Artificial Intelligence
Information Retrieval
Open-vocabulary object detection (OVD) models offer remarkable flexibility by detecting objects from arbitrary text queries. However, their zero-shot performance in specialized domains like Remote Sensing (RS) is often compromised by the inherent ambiguity of natural language, limiting critical downstream applications. For instance, an OVD model may struggle to distinguish between fine-grained classes such as "fishing boat" and "yacht" since their embeddings are similar and often inseparable. This can hamper specific user goals, such as monitoring illegal fishing, by producing irrelevant detections. To address this, we propose a cascaded approach that couples the broad generalization of a large pre-trained OVD model with a lightweight few-shot classifier. Our method first employs the zero-shot model to generate high-recall object proposals. These proposals are then refined for high precision by a compact classifier trained in real-time on only a handful of user-annotated examples - drastically reducing the high costs of RS imagery annotation.The core of our framework is FLAME, a one-step active learning strategy that selects the most informative samples for training. FLAME identifies, on the fly, uncertain marginal candidates near the decision boundary using density estimation, followed by clustering to ensure sample diversity. This efficient sampling technique achieves high accuracy without costly full-model fine-tuning and enables instant adaptation, within less then a minute, which is significantly faster than state-of-the-art alternatives.Our method consistently surpasses state-of-the-art performance on RS benchmarks, establishing a practical and resource-efficient framework for adapting foundation models to specific user needs.
title On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration
topic Machine Learning
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2510.17670