Amortized Bayesian Prototype Meta-learning: A New Probabilistic Meta-learning Approach to Few-shot Image Classification-猫眼课题宝

DOI：

发表时间：

2021

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Z. Sun;Jijie Wu;Xiaoxu Li;Wenming Yang;Jing-Hao Xue

概率元学习方法最近在少量图像分类中取得了令人印象深刻的成功。然而，它们为神经网络的权重引入了大量的随机变量，从而给计算和推理带来了严峻的挑战。本文提出了一种新的概率元学习方法——平摊贝叶斯原型元学习。与以前的方法相比，我们为潜在类原型引入了少量的随机变量，而不是为网络权重引入了大量的随机变量；我们学习以平摊推理的方式学习这些潜在原型的后验分布，而不需要额外的平摊网络，这样我们就可以很容易地在少量标记样本的条件下近似它们的后验，无论何时在元训练或元测试阶段。该方法无需任何预训练即可实现端到端训练。与其他概率元学习方法相比，我们提出的方法具有更少随机变量的可解释性，同时仍然能够在各种基准数据集上实现少量图像分类问题的竞争性性能。通过烧蚀研究也证明了其良好的鲁棒性和预测不确定性。

Probabilistic meta-learning methods recently have achieved impressive success in few-shot image classiﬁcation. However, they introduce a huge number of random variables for neural network weights and thus severe computational and inferential challenges. In this paper, we propose a novel probabilistic meta-learning method called amortized Bayesian prototype meta-learning. In contrast to previous methods, we introduce only a small number of random variables for latent class prototypes rather than a huge number for network weights; we learn to learn the posterior distributions of these latent prototypes in an amortized inference way with no need for an extra amortization network, such that we can easily approximate their posteriors conditional on few labeled samples, whenever at meta-training or meta-testing stage. The proposed method can be trained end-to-end without any pre-training. Compared with other probabilistic meta-learning methods, our proposed approach is more interpretable with much less random variables, while still be able to achieve competitive performance for few-shot image classiﬁcation problems on various benchmark datasets. Its excellent robustness and predictive uncertainty are also demonstrated through ablation studies.

Amortized Bayesian Prototype Meta-learning: A New Probabilistic Meta-learning Approach to Few-shot Image Classification

文献摘要

相似文献