Learning to Learn with Variational Information Bottleneck for Domain Generalization
Learning to Learn with Variational Information Bottleneck for Domain Generalization
复制标题
DOI：
10.1007/978-3-030-58607-2_12
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Yingjun Du;Jun Xu;Huan Xiong;Qiang Qiu;Xiantong Zhen;Cees G. M. Snoek;Ling Shao
中科院分区：
文献类型：
--
作者：
Yingjun Du;Jun Xu;Huan Xiong;Qiang Qiu;Xiantong Zhen;Cees G. M. Snoek;Ling Shao
领域泛化模型学习将泛化到以前未见过的领域，但受到预测不确定性和领域漂移的影响。在本文中，我们解决了这两个问题。提出了一种用于领域泛化的概率元学习模型，其中跨域共享的分类器参数被建模为分布。这使得能够更好地处理不可见领域上的预测不确定性。为了处理域迁移，我们通过提出的元变分信息瓶颈原理来学习域不变表示，我们称之为MetaVIB。MetaVIB通过利用领域泛化的元学习设置，从新的互信息的变化界中派生出来。通过情景训练，MetaVIB学习逐渐缩小领域差距以建立领域不变的表示，同时最大化预测精度。我们在三个跨域视觉识别基准上进行了实验。全面的消融研究证实了MetaVIB对域泛化的好处。比较结果表明，我们的方法比以前的方法具有更好的性能。
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. In this paper, we address both problems. We introduce a probabilistic meta-learning model for domain generalization, in which classifier parameters shared across domains are modeled as distributions. This enables better handling of prediction uncertainty on unseen domains. To deal with domain shift, we learn domain-invariant representations by the proposed principle of meta variational information bottleneck, we call MetaVIB. MetaVIB is derived from novel variational bounds of mutual information, by leveraging the meta-learning setting of domain generalization. Through episodic training, MetaVIB learns to gradually narrow domain gaps to establish domain-invariant representations, while simultaneously maximizing prediction accuracy. We conduct experiments on three benchmarks for cross-domain visual recognition. Comprehensive ablation studies validate the benefits of MetaVIB for domain generalization. The comparison results demonstrate our method outperforms previous approaches consistently.