面向目标检测的可移植主动学习
Portable Active Learning for Object Detection
PAL 只依赖推理输出（提案框与分类分数）构造类别级不确定性，并用图像级熵、类别多样性与相似度做批次筛选，因此可直接套用到任意检测器（含开放词表或域偏移场景）的标注预算分配上，无需改动训练管线。
原文依据 PAL combines class-wise instance uncertainty with image-level diversity to guide data selection.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论标注边界框代价高昂，限制了目标检测的可扩展性。在实际应用中，还需在尽量减少人工投入的同时保持高精度，这使该挑战更加严峻。以往的主动学习方法往往依赖模型特征，或修改检测器内部结构与训练计划，增加了集成开销。此外，它们很少联合利用图像级信号、类别不平衡线索与实例级不确定性来进行全面选择。我们提出可移植主动学习（PAL），这是一个与检测器无关、易于移植的框架，仅基于推理输出运行。PAL 将类别级实例不确定性与图像级多样性相结合来指导数据选择。在每一轮中，PAL 训练轻量级的类别专属逻辑回归分类器以区分真正例与假正例，为候选框生成基于熵的不确定性分数。随后利用全局图像熵、类别多样性与图像相似度对候选图像进行筛选，得到既具信息量又具多样性的批次。PAL 无需改动模型内部结构或训练流程，确保了对各类检测器的广泛兼容性。在 COCO、PASCAL VOC 与 BDD100K 上的大量实验表明，与现有主动学习基线相比，PAL 持续提升了标签效率与检测精度，使其成为在真实场景中可扩展且高性价比地部署目标检测的实用方案。
英文原文摘要 1491 字符
Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods often depend on model features or modify detector internals and training schedules, increasing integration overhead. Moreover, they rarely jointly exploit the benefits of image-level signals, class-imbalance cues, and instance-level uncertainty for comprehensive selection. We present Portable Active Learning (PAL), a detector-agnostic, easily portable framework that operates solely on inference outputs. PAL combines class-wise instance uncertainty with image-level diversity to guide data selection. At each round, PAL trains lightweight class-specific logistic classifiers to distinguish true from false positives, producing entropy-based uncertainty scores for proposals. Candidate images are then refined using global image entropy, class diversity, and image similarity, yielding batches that are both informative and diverse. PAL requires no changes to model internals or training pipelines, ensuring broad compatibility across detectors. Extensive experiments on COCO, PASCAL VOC, and BDD100K demonstrate that PAL consistently improves label efficiency and detection accuracy compared to existing active learning baselines, making it a practical solution for scalable and cost-effective deployment of object detection in real-world settings.