Domain Generalization (DG) is a challenging task in machine learning that
requires a coherent ability to comprehend shifts across various domains through
extraction of domain-invariant features. DG performance is typically evaluated
by performing image classification in domains of various image styles. However,
current methodology lacks quantitative understanding about shifts in stylistic
domain, and relies on a vast amount of pre-training data, such as ImageNet1K,
which are predominantly in photo-realistic style with weakly supervised class
labels. Such a data-driven practice could potentially result in spurious
correlation and inflated performance on DG benchmarks. In this paper, we
introduce a new DG paradigm to address these risks. We first introduce two new
quantitative measures ICV and IDD to describe domain shifts in terms of
consistency of classes within one domain and similarity between two stylistic
domains. We then present SuperMarioDomains (SMD), a novel synthetic
multi-domain dataset sampled from video game scenes with more consistent
classes and sufficient dissimilarity compared to ImageNet1K. We demonstrate our
DG method SMOS. SMOS first uses SMD to train a precursor model, which is then
used to ground the training on a DG benchmark. We observe that SMOS contributes
to state-of-the-art performance across five DG benchmarks, gaining large
improvements to performances on abstract domains along with on-par or slight
improvements to those on photo-realistic domains. Our qualitative analysis
suggests that these improvements can be attributed to reduced distributional
divergence between originally distant domains. Our data are available at
this https URL .

在这篇论文中，我们介绍了一种新的领域综合范式，该方法通过提取领域不变特征来解决机器学习中的领域泛化问题，并引入了两个新的定量衡量标准 ICV 和 IDD 来描述风格领域的变化，同时提出了 SuperMarioDomains（SMD）这一新的合成多领域数据集，为 DG 方法 SMOS 的训练提供了预备模型，最终取得了在五个 DG 基准测试上的最新成果，对于抽象领域的性能大幅提升，并在逼真领域上保持相当水平或稍有改善。