arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.08249cs.AI
收藏

面向小数据集图像分类学习的参数化损失函数演化方法

Evolving parametrized Loss for Image Classification Learning on Small Datasets

Zhaoyang Hai, Xiabi Liu

AI总结:

本文提出元损失网络(MLN),将参数化损失函数嵌入分类学习框架,并用演化策略算法优化该损失函数,使小数据集上训练的分类器获得更好泛化效果,实验表明其优于交叉熵和均方误差。

摘要:

本文提出了一种元学习方法,用于演化参数化损失函数,称为元损失网络(Meta-Loss Network,MLN),以训练小数据集上的图像分类学习。在该方法中,MLN 作为可微目标函数嵌入分类学习框架中。MLN 通过演化策略算法(Evolutionary Strategy,ES)演化为优化后的损失函数,使得一个以最小化该损失为优化目标的分类器能够获得良好的泛化效果。分类器在小训练数据集上通过随机梯度下降(Stochastic Gradient Descent,SGD)最小化 MLN 进行学习,随后 MLN 根据小数据集更新后的分类器在大型验证数据集上的精度进行演化。为了评估该方法,MLN 在从 FashionMNIST 采样的大量小样本学习任务上进行训练,并在从 FashionMNIST 和 CIFAR10 采样的验证任务上进行测试。实验结果表明,与经典的交叉熵误差和均方误差相比,MLN 有效提升了泛化性能。

英文摘要:

This paper proposes a meta-learning approach to evolving a parametrized loss function, which is called Meta-Loss Network (MLN), for training the image classification learning on small datasets. In our approach, the MLN is embedded in the framework of classification learning as a differentiable objective function. The MLN is evolved with the Evolutionary Strategy algorithm (ES) to an optimized loss function, such that a classifier, which optimized to minimize this loss, will achieve a good generalization effect. A classifier learns on a small training dataset to minimize MLN with Stochastic Gradient Descent (SGD), and then the MLN is evolved with the precision of the small-dataset-updated classifier on a large validation dataset. In order to evaluate our approach, the MLN is trained with a large number of small sample learning tasks sampled from FashionMNIST and tested on validation tasks sampled from FashionMNIST and CIFAR10. Experiment results demonstrate that the MLN effectively improved generalization compared to classical cross-entropy error and mean squared error.

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。

↑