重新审视未知类：迈向高效且有效的开放集主动学习
Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learning
提出一种无需独立开放集检测器的统一主动学习框架，利用冻结的对比预训练特征空间进行标签引导聚类，并用 Dirichlet 校准的辅助检测头联合建模已知与未知类，可直接用于视觉任务中标注预算受限下的开放世界数据筛选。
原文依据 E^2OAL first uncovers the latent class structure of unknowns through label-guided clustering in a frozen contrastively pre-trained feature space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论开放集主动学习（OSAL）旨在无标注数据可能包含未见类别时，识别出信息量大的样本进行标注——这是安全关键和开放世界场景中的常见挑战。现有方法通常依赖单独训练的开放集检测器，带来大量训练开销，并忽视了已标注未知类对改进已知类学习的监督价值。本文提出 E^2OAL（高效且有效的开放集主动学习），一个统一且无需检测器的框架，充分利用已标注未知类来实现更强的监督和更可靠的查询。E^2OAL 首先在冻结的对比预训练特征空间中通过标签引导聚类揭示未知类的潜在类别结构，并由结构感知的 F1-product 目标进行优化。为利用已标注未知类，它采用 Dirichlet 校准的辅助检测头联合建模已知和未知类别，同时改善置信度校准和已知类判别。在此基础上，logit-margin 纯度分数估计已知类的似然以构建高纯度候选池，而 OSAL 专用的信息量指标优先选择部分模糊但可靠的样本。这些组件共同构成灵活的两阶段查询策略，具有自适应精度控制和极小的超参数敏感性。在多个 OSAL 基准上的大量实验表明，E^2OAL 在准确率、效率和查询精度上持续超越最优方法，突显了其在实际应用中的有效性和实用性。代码见 github.com/chenchenzong/E2OAL。
英文原文摘要 1710 字符
Open-set active learning (OSAL) aims to identify informative samples for annotation when unlabeled data may contain previously unseen classes--a common challenge in safety-critical and open-world scenarios. Existing approaches typically rely on separately trained open-set detectors, introducing substantial training overhead and overlooking the supervisory value of labeled unknowns for improving known-class learning. In this paper, we propose E^2OAL (Effective and Efficient Open-set Active Learning), a unified and detector-free framework that fully exploits labeled unknowns for both stronger supervision and more reliable querying. E^2OAL first uncovers the latent class structure of unknowns through label-guided clustering in a frozen contrastively pre-trained feature space, optimized by a structure-aware F1-product objective. To leverage labeled unknowns, it employs a Dirichlet-calibrated auxiliary head that jointly models known and unknown categories, improving both confidence calibration and known-class discrimination. Building on this, a logit-margin purity score estimates the likelihood of known classes to construct a high-purity candidate pool, while an OSAL-specific informativeness metric prioritizes partially ambiguous yet reliable samples. These components together form a flexible two-stage query strategy with adaptive precision control and minimal hyperparameter sensitivity. Extensive experiments across multiple OSAL benchmarks demonstrate that E^2OAL consistently surpasses state-of-the-art methods in accuracy, efficiency, and query precision, highlighting its effectiveness and practicality for real-world applications. The code is available at github.com/chenchenzong/E2OAL.