Scholarlink

<p>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 <b>C</b>ontrastive-based <b>D</b>isentanglement method for <b>D</b>omain <b>G</b>eneralization (<b>CDDG</b>), to effectively utilize the disentangled features to exploit the over-looked domain-specific features, and thus facilitate 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, including PACS, VLCS, Office-Home, TerraIncognita and DomainNet, have demonstrated 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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Embracing the overlooked: harnessing feature disentanglement for cross-domain learning

  • 期刊论文

  • 发表日期：

    2026年2月20日

查看全文
  • Hao Chen,
  • Junbo Zhao

摘要

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 for Domain Generalization (CDDG), to effectively utilize the disentangled features to exploit the over-looked domain-specific features, and thus facilitate 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, including PACS, VLCS, Office-Home, TerraIncognita and DomainNet, have demonstrated 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.