IEEE Trans Neural Netw Learn Syst. 2021 Aug;32(8):3458-3470. doi: 10.1109/TNNLS.2020.3011526. Epub 2021 Aug 3.
Few-shot learning aims to learn a well-performing model from a few labeled examples. Recently, quite a few works propose to learn a predictor to directly generate model parameter weights with episodic training strategy of meta-learning and achieve fairly promising performance. However, the predictor in these works is task-agnostic, which means that the predictor cannot adjust to novel tasks in the testing phase. In this article, we propose a novel meta-learning method to learn how to learn task-adaptive classifier-predictor to generate classifier weights for few-shot classification. Specifically, a meta classifier-predictor module, (MPM) is introduced to learn how to adaptively update a task-agnostic classifier-predictor to a task-specialized one on a novel task with a newly proposed center-uniqueness loss function. Compared with previous works, our task-adaptive classifier-predictor can better capture characteristics of each category in a novel task and thus generate a more accurate and effective classifier. Our method is evaluated on two commonly used benchmarks for few-shot classification, i.e., miniImageNet and tieredImageNet. Ablation study verifies the necessity of learning task-adaptive classifier-predictor and the effectiveness of our newly proposed center-uniqueness loss. Moreover, our method achieves the state-of-the-art performance on both benchmarks, thus demonstrating its superiority.
少样本学习旨在从少数带标签的示例中学习表现良好的模型。最近，相当多的工作提出学习一个预测器，通过元学习的阶段性训练策略直接生成模型参数权重，从而取得相当有前景的性能。然而，这些工作中的预测器是任务不可知的，这意味着预测器不能在测试阶段适应新任务。在本文中，我们提出了一种新的元学习方法，学习如何学习任务自适应分类器-预测器，以生成用于少样本分类的分类器权重。具体来说，引入了一个元分类器-预测器模块（MPM），以学习如何自适应地将任务不可知的分类器-预测器更新为新任务上的任务专门化的分类器-预测器，使用新提出的中心唯一性损失函数。与以前的工作相比，我们的任务自适应分类器-预测器可以更好地捕捉新任务中每个类别的特征，从而生成更准确和有效的分类器。我们的方法在两个常用的少样本分类基准上进行了评估，即 miniImageNet 和 tieredImageNet。消融研究验证了学习任务自适应分类器-预测器的必要性和我们新提出的中心唯一性损失的有效性。此外，我们的方法在两个基准上都取得了最先进的性能，从而证明了其优越性。
