ActiveAugment：深度学习中用于增强选择的在线主动学习框架
ActiveAugment: Online Active Learning for Augmentation Selection in Deep Learning
查看机构详情
- Pioneer Centre for AI（先锋人工智能中心）
- University of Copenhagen（哥本哈根大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
ActiveAugment是将增强选择视为在线主动学习的统一框架，在多领域基准数据集上，它优于多种现有增强策略，尤其在低标注预算和医学成像场景中表现突出，具备强跨域适应性。
中文摘要 AI 辅助
数据增强是深度学习流程的基石，但现有策略将其视为静态、与模型无关的预处理步骤，要么依赖昂贵的特定数据集策略搜索，要么无论模型已学习到什么，都均匀随机应用变换。我们提出ActiveAugment，一个将增强选择视为在线主动学习问题的统一框架。对于每个训练小批量，ActiveAugment生成候选增强视图池，并结合模型的预测不确定性和增强诱导的特征差异对每个候选进行评分。针对每个样本，选择当前模型最脆弱的增强，随后模型采用联合监督分类和监督对比目标进行训练，该目标对所选增强强制类内不变性，同时保持类间分离。我们在涵盖自然和医学成像的8个基准数据集上评估ActiveAugment，使用CNN和Transformer架构，覆盖三种训练模式（从头训练、全微调、线性探测），并比较8种用于增强评分的主动选择策略。在跨所有领域和预算的受控增强偏移下，ActiveAugment的性能优于AutoAugment、RandAugment和TrivialAugment，在低标注预算下增益最为显著。在数据稀缺且相对于自然图像预训练模型的域偏移较大的医学成像数据集上，ActiveAugment的测试F1值高于所有基线，展现出强大的跨域适应性。我们的分析表明，增强选择策略在训练过程中会发生有意义的演变，且策略选择对泛化有直接影响。代码可在该httpsURL获取。
英文摘要
Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, either relying on expensive dataset-specific policy search or applying transformations uniformly at random, regardless of what the model has already learned. We introduce ActiveAugment, a unified framework that treats augmentation selection as an online active learning problem. For each training minibatch, ActiveAugment generates a pool of candidate augmented views and scores each candidate using a combination of the model's predictive uncertainty and the feature discrepancy induced by the augmentation. The augmentation under which the current model is most fragile is selected per sample, and the model is then trained with a joint supervised classification and supervised contrastive objective that enforces intra-class invariance to the selected augmentations while maintaining inter-class separation. We evaluate ActiveAugment on eight benchmark datasets spanning natural and medical imaging, using CNN and transformer architectures across three training regimes (training from scratch, full fine-tuning, and linear probing), and comparing eight active selection strategies for augmentation scoring. ActiveAugment outperforms AutoAugment, RandAugment, and TrivialAugment under controlled augmentation shifts across all domains and budgets, with the most pronounced gains at low labelling budgets. On medical imaging datasets, where data is scarce and domain shift relative to natural-image pretrained models is large, ActiveAugment achieves higher test F1 than all baselines, demonstrating strong cross-domain adaptability. Our analysis reveals that the augmentation selection policy evolves meaningfully during training and that strategy choice has a direct impact on generalisation. Code is available at: https://github.com/noahvide/ActiveAugment.
