首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Learning to Learn Adaptive Classifier–Predictor for Few-Shot Learning
【24h】

Learning to Learn Adaptive Classifier–Predictor for Few-Shot Learning

机译:学习学习自适应分类器 - 预测少量学习

获取原文
获取原文并翻译 | 示例
           

摘要

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.
机译:很少拍摄的学习旨在从一些标记的例子中学习一个表现良好的模型。最近,相当多的作品建议学习预测指标,以便直接生成模型参数权重,以荟萃学习的情节训练策略,实现相当明显的表现。然而,这些作品中的预测器是任务不可行的,这意味着预测器无法在测试阶段调整到新的任务。在本文中,我们提出了一种新的元学习方法,用于学习如何学习任务 - 自适应分类器 - 预测器以生成几次拍摄分类的分类器权重。具体地,引入了元分类器 - 预测器模块(MPM),以了解如何在具有新提出的中心唯一性​​损失函数的新任务上自适应地将任务不可行的分类器 - 预测器自适应地更新为任务专用。与以前的作品相比,我们的任务 - 自适应分类器 - 预测器可以更好地捕获新的任务中每个类别的特征,从而产生更准确且有效的分类器。我们的方法是对几个常用的基准进行评估,用于几次拍摄的分类,即MiniimageNet和TieredimageNet。消融研究验证了学习任务 - 自适应分类器的必要性 - 预测性,以及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实现了最先进的性能,从而展示了其优越性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号