Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of training data. Because data distributions can change dynamically in real-life applications once a learned model is deployed, in this paper we are interested in single-source domain generalization (SDG) which aims to develop deep learning algorithms able to generalize from a single training domain where no information about the test domain is available at training time. Firstly, we design two simple MNISTbased SDG benchmarks, namely MNIST Color SDG-MP and MNIST Color SDG-UP, which highlight the two different fundamental SDG issues of increasing difficulties: 1) a class-correlated pattern in the training domain is missing (SDG-MP), or 2) uncorrelated with the class (SDG-UP), in the testing data domain. This is in sharp contrast with the current domain generalization (DG) benchmarks which mix up different correlation and variation factors and thereby make hard to disentangle success or failure factors when benchmarking DG algorithms. We further evaluate several state-of-the-art SDG algorithms through our simple benchmark, namely MNIST Color SDG-MP, and show that the issue SDG-MP is largely unsolved despite of a decade of efforts in developing DG algorithms. Finally, we also propose a partially reversed contrastive loss to encourage intra-class diversity and find less strongly correlated patterns, to deal with SDG-MP and show that the proposed approach is very effective on our MNIST Color SDG-MP benchmark.
翻译:传统的深层次学习算法往往无法在培训数据领域之外测试时普遍化。因为数据分布一旦运用了学习模式,就会在现实应用中发生动态变化。在本文件中,我们感兴趣的是单一源域一般化(SDG),其目的是从单一培训领域发展深层次的学习算法,从培训时没有关于测试领域的信息的单一培训领域进行普及。首先,我们设计基于MNIST的简单标准,即MNIST颜色 SDG-MP 和MNIST 颜色 SDG-UP,这凸显了两个日益困难的两个不同的SDG基本问题:(1) 培训领域缺少与阶级相关的模式(SDG-MP),或者2 与测试数据领域的班级(SDG-UP)不相关。这与目前的域一般化(DG)基准形成鲜明对比,这些基准混合了不同的关联和变异因素,因此很难在确定DG算法基准时找出成功或失败的因素。我们进一步评估了几个的SDG(SDG)算算法通过我们简单的基准基准,即,最终的SDG-DG-DG-DG-DG-DG-DM(C-D-D-D-DG-DG-C-DM-C-DG-DG-C-C-C-C-C-C-C-C-DMDD-D-D-D-D-C-C-C-C-C-C-C-C-D-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-D-D-D-D-D-D-C-D-D-D-D-C-C-C-C-C-DGD-D-C-C-C-C-C-C-C-C-C-C-C-C-C-C-D-D-C-D-D-D-D-D-C-D-D-D-D-D-D-D-D-D-C-D-D