GALAXY：极端场景下的基于图的主动学习
GALAXY: Graph-based Active Learning at the Extreme
AI总结：
针对开放世界中的极端类别不平衡问题，提出融合图主动学习与深度学习的 GALAXY 策略，以自适应选择更类别平衡的样本，并在视觉分类实验中优于现有深度主动学习方法。
摘要：
主动学习是一种标签高效的方法，用于训练高效模型，同时以交互方式仅选择未标记数据的小型子集进行标记和训练。在“开放世界”设定中，感兴趣的类别可能只占整个数据集的一小部分——大多数数据可被视为分布外或不相关类别。这导致极端的类别不平衡，而我们的理论和方法正聚焦于这一核心问题。我们提出了一种名为 GALAXY（Graph-based Active Learning At the eXtrEme，极端场景下的基于图的主动学习）的新型主动学习策略，它融合了基于图的主动学习与深度学习的思想。与大多数其他主动学习方法相比，GALAXY 能够自动且自适应地选择类别更加平衡的样本进行标记。我们的理论表明，GALAXY 执行的是一种精细化的不确定性采样形式，相较于普通不确定性采样，它能收集类别平衡得多的数据集。在实验方面，我们在由流行数据集生成的不平衡视觉分类设定中，证明了 GALAXY 相对于现有最先进深度主动学习算法的优越性。
英文摘要：
Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a small fraction of the overall dataset -- most of the data may be viewed as an out-of-distribution or irrelevant class. This leads to extreme class-imbalance, and our theory and methods focus on this core issue. We propose a new strategy for active learning called GALAXY (Graph-based Active Learning At the eXtrEme), which blends ideas from graph-based active learning and deep learning. GALAXY automatically and adaptively selects more class-balanced examples for labeling than most other methods for active learning. Our theory shows that GALAXY performs a refined form of uncertainty sampling that gathers a much more class-balanced dataset than vanilla uncertainty sampling. Experimentally, we demonstrate GALAXY's superiority over existing state-of-art deep active learning algorithms in unbalanced vision classification settings generated from popular datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
