清洗池子：深度主动学习中未标注池的渐进式过滤
Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning
对视觉研究者而言，REFINE 提供了一种无需预先知道哪种采样策略最优的集成式主动学习流程：先用多策略集成对未标注池做渐进式过滤，再用覆盖度选择挑批，可直接套用到视觉基础模型（如 CLIP、DINOv2）的标注预算受限微调场景，且过滤后的池子能提升任意单一 AL 策略的表现。
原文依据 progressive filtering serves as a powerful preprocessing step that improves the performance of any individual AL strategy applied to the refined pool
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有主动学习（AL）策略捕捉的是根本不同的数据价值概念，例如不确定性或代表性。因此，策略的有效性会随数据集、模型乃至 AL 轮次的不同而显著变化。固守单一策略存在性能次优的风险，因为没有任何单一策略能在整个 AL 过程中始终占优。我们提出 REFINE，一种集成式 AL 方法，它组合多种策略，且无需预先知道哪一种表现最佳。在每个 AL 轮次中，REFINE 分两个阶段运行：（1）渐进式过滤，通过考虑 AL 策略的集成来迭代地精炼未标注池，保留捕捉不同价值概念的有希望的候选样本。（2）基于覆盖度的选择，随后从这个精炼后的池子中选出最终批次，确保此前识别出的所有价值概念都被纳入考量。在 6 个分类数据集和 3 个基础模型上的大量实验表明，REFINE 始终优于单一策略和现有集成方法。值得注意的是，渐进式过滤可作为一种强大的预处理步骤，提升应用于精炼池上的任意单一 AL 策略的性能，我们在一个音频频谱图分类用例上对此进行了验证。最后，REFINE 的集成可以很容易地用即将出现的最优 AL 策略进行扩展。
英文原文摘要 1391 字符
Existing active learning (AL) strategies capture fundamentally different notions of data value, e.g., uncertainty or representativeness. Consequently, the effectiveness of strategies can vary substantially across datasets, models, and even AL cycles. Committing to a single strategy risks suboptimal performance, as no single strategy dominates throughout the entire AL process. We introduce REFINE, an ensemble AL method that combines multiple strategies without knowing in advance which will perform best. In each AL cycle, REFINE operates in two stages: (1) Progressive filtering iteratively refines the unlabeled pool by considering an ensemble of AL strategies, retaining promising candidates capturing different notions of value. (2) Coverage-based selection then chooses a final batch from this refined pool, ensuring all previously identified notions of value are accounted for. Extensive experiments across 6 classification datasets and 3 foundation models show that REFINE consistently outperforms individual strategies and existing ensemble methods. Notably, progressive filtering serves as a powerful preprocessing step that improves the performance of any individual AL strategy applied to the refined pool, which we demonstrate on an audio spectrogram classification use case. Finally, the ensemble of REFINE can be easily extended with upcoming state-of-the-art AL strategies.