跳到正文
arXiv cs.AI· Mohammad Mirzaee, Mehrshad Fallah Estalkhzir, Mohammad Reza Mohammadi·· 10 小时前AI 评分22

基于基础模型初始数据选择的主动学习性能提升方法

Enhancing Active Learning Performance with Initial Data Selection Based on Foundation Models

AI 导读

研究提出一种主动学习框架,用 YOLO-World 模型的特征聚类替代初始轮次的不确定性采样,并按 objectness 分数精炼图像,后续轮次改用一致性采样。在 NWPU VHR-10 数据集上,该方法图像级评估的 mAP50 平均提升 6.6%,图像精炼在目标级评估中提升约 11%。算法实现已公开。

正文 · 原文

View PDF HTML (experimental)

Abstract:In active object detection, selecting the initial labeled pool is essential, especially in complex datasets with expensive labeling and low resource budget. This study presents an active learning framework designed to optimize the initial training cycle of active learning for the object detection task. Our approach diverges from traditional methods by utilizing feature-based clustering from the YOLO-World model and refining images based on objectness scores rather than relying on uncertainty sampling in the initial cycle. This approach focuses on finding samples with various features and emphasizes training in areas where the foundation model is most confident. Doing so helps the model better understand different types of objects. For subsequent cycles, we employ a consistency-based sampling technique to maintain the robustness of the training process. To evaluate our method, we use two complex datasets called Aquarium and NWPU VHR-10, which are well known for their diverse object sizes and challenging conditions. In the NWPU dataset, our method increases mAP50 by an average of 6.6% in image-based evaluation. Moreover, the image refinement method shows an improvement of approximately 11% in object-based evaluation. The results show improvements in model performance and labeling time, demonstrating the advantages of using foundation models in early cycles of active learning. An implementation of the algorithm is available at this https URL
Comments: 26 pages, 18 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24384 [cs.CV]
  (or arXiv:2611.24384v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.24384

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mohammad Mirzaee [view email]
[v1] Wed, 18 Nov 2026 13:15:03 UTC (1,897 KB)

来源:arXiv cs.AI · arxiv.org