Given the large-scale data and the high annotation cost,
pretraining-finetuning becomes a popular paradigm in multiple computer vision
tasks. Previous research has covered both the unsupervised pretraining and
supervised finetuning in this paradigm, while little attention is paid to
exploiting the annotation budget for finetuning. To fill in this gap, we
formally define this new active finetuning task focusing on the selection of
samples for annotation in the pretraining-finetuning paradigm. We propose a
novel method called ActiveFT for active finetuning task to select a subset of
data distributing similarly with the entire unlabeled pool and maintaining
enough diversity by optimizing a parametric model in the continuous space. We
prove that the Earth Mover's distance between the distributions of the selected
subset and the entire data pool is also reduced in this process. Extensive
experiments show the leading performance and high efficiency of ActiveFT
superior to baselines on both image classification and semantic segmentation.
Our code is released at this https URL

该研究提出了一种新的主动微调任务，在预训练 - 微调范式下注重选择注释样本，通过优化连续空间中的参数模型来选择类似于整个未标记池的数据子集并保持足够的多样性，实验证明了该方法在计算机视觉任务上具有领先的性能和高效率。

主动微调：在预训练 - 微调模式中利用注释预算

Active Finetuning: Exploiting Annotation Budget in the  Pretraining-Finetuning Paradigm

Preserving maximal information is one of principles of designing
self-supervised learning methodologies. To reach this goal, contrastive
learning adopts an implicit way which is contrasting image pairs. However, we
believe it is not fully optimal to simply use the contrastive estimation for
preservation. Moreover, it is necessary and complemental to introduce an
explicit solution to preserve more information. From this perspective, we
introduce Preservational Learning to reconstruct diverse image contexts in
order to preserve more information in learned representations. Together with
the contrastive loss, we present Preservational Contrastive Representation
Learning (PCRL) for learning self-supervised medical representations. PCRL
provides very competitive results under the pretraining-finetuning protocol,
outperforming both self-supervised and supervised counterparts in 5
classification/segmentation tasks substantially.

本文介绍了一种自我监督学习方法 —— Preservational Contrastive Representation Learning (PCRL)，通过引入 Preservational Learning 来重建不同的图像空间，并与对比损失联合训练自监督医学表示方法。在 5 个分类 / 分割任务中，PCRL 在预训练 - 微调协议下提供了非常有竞争力的结果，优于自我监督和有监督方法。