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

arXiv: https://arxiv.org/abs/2510.17670 · HTML: https://mlsanity.com/paper/2510.17670/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Open-Vocabulary DETR with Conditional Matching](https://mlsanity.com/paper/2203.11876/) (2022)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data](https://mlsanity.com/paper/2210.12634/) (2022)
- [Active Learning for Deep Object Detection](https://mlsanity.com/paper/1809.09875/) (2018)
- [Revisiting Few-Shot Object Detection with Vision-Language Models](https://mlsanity.com/paper/2312.14494/) (2023)
- [Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery](https://mlsanity.com/paper/2403.05381/) (2024)
- [A Recipe for Improving Remote Sensing VLM Zero Shot Generalization](https://mlsanity.com/paper/2503.08722/) (2025)
- [Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime](https://mlsanity.com/paper/2307.09562/) (2023)

## Built on by (most cited first, 1 of 1)

- [The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning](https://mlsanity.com/paper/2607.12177/) (2026)

## Abstract (arXiv)

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.