Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source domains via domain adversarial learning (DAL). However, inspired by causal mechanisms, we find that previous methods ignore the implicit insignificant non-causal factors hidden in the common features. This is mainly due to the single-view nature of DAL. In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data. To summarize, we propose a Multi-view Adversarial Discriminator (MAD) based domain generalization model, consisting of a Spurious Correlations Generator (SCG) that increases the diversity of source domain by random augmentation and a Multi-View Domain Classifier (MVDC) that maps features to multiple latent spaces, such that the non-causal factors are removed and the domain-invariant features are purified. Extensive experiments on six benchmarks show our MAD obtains state-of-the-art performance.

翻译：领域偏移会降低目标检测模型在实际应用中的性能。为减轻领域偏移的影响，以往大量工作尝试通过领域对抗学习（DAL）从源领域中解耦并学习领域不变（共同）特征。然而，受因果机制启发，我们发现以往方法忽略了隐含于共同特征中的隐式非显著非因果因素。这主要源于DAL的单视角特性。本文提出一种思路：通过对源领域进行多视角对抗训练来移除共同特征中的非因果因素，因为观察到由于数据的多模态结构，这些非显著非因果因素在其他潜在空间（视角）中可能仍具有显著性。综上，我们提出一种基于多视角对抗判别器（MAD）的领域泛化模型，该模型包含：通过随机增广提升源领域多样性的虚假相关性生成器（SCG），以及将特征映射至多个潜在空间的多视角领域分类器（MVDC），从而移除非因果因素并纯化领域不变特征。在六个基准数据集上的大量实验表明，本方法的MAD模型取得了当前最优性能。