Distributional shift between domains poses great challenges to modern machine learning algorithms. The domain generalization (DG) signifies a popular line targeting this issue, where these methods intend to uncover universal patterns across disparate distributions. Noted, the crucial challenge behind DG is the existence of irrelevant domain features, and most prior works overlook this information. Motivated by this, we propose a novel contrastive-based disentanglement method CDDG, to effectively utilize the disentangled features to exploit the over-looked domain-specific features, and thus facilitating the extraction of the desired cross-domain category features for DG tasks. Specifically, CDDG learns to decouple inherent mutually exclusive features by leveraging them in the latent space, thus making the learning discriminative. Extensive experiments conducted on various benchmark datasets demonstrate the superiority of our method compared to other state-of-the-art approaches. Furthermore, visualization evaluations confirm the potential of our method in achieving effective feature disentanglement.

翻译：域间分布偏移对现代机器学习算法提出了巨大挑战。领域泛化（DG）作为解决该问题的热门研究方向，旨在挖掘不同分布间的通用模式。值得注意的是，DG背后的关键挑战在于无关域特征的存在，而现有研究大多忽略了这一信息。基于此，我们提出了一种新颖的基于对比学习的解耦方法CDDG，通过有效利用解耦特征来挖掘被忽视的特定域特征，从而促进DG任务中期望的跨域类别特征提取。具体而言，CDDG通过在潜在空间中利用固有的互斥特征进行解耦学习，使学习过程更具判别性。在多个基准数据集上的大量实验表明，我们的方法相较于现有最先进方法具有优越性。此外，可视化评估证实了该方法在实现有效特征解耦方面的潜力。