Scholarlink

<p>In real-world scenarios, few-shot unsupervised domain adaptation (FUDA) faces the dual challenges of limited source supervision and poor target generalization due to the extremely scarce annotated source samples. Existing methods often overlook the restricted learning capacity caused by sparse source labels or fail to effectively utilize the structural information within the target domain to enhance discriminative performance. To address these issues, we propose a novel method, Collaborative Pseudo-label Transfer (CPLT), which jointly improves cross-domain adaptation under few-shot UDA settings. CPLT comprises two key components: a Pseudo-label Guided Source Augmentation (PGSA) mechanism that iteratively selects high-confidence target samples to augment the source domain and strengthen initial representation learning, and a Target-aware Discriminative Modeling (TADM) that leverages pseudo-labeled target data to construct auxiliary classifiers for enhanced inter-class discrimination and reduced misclassification under domain shift. Experiments on three widely used FUDA benchmarks validate the superior performance of CPLT, achieving average accuracy gains of +3.5% on Office-31, +1.4% on Office-Home, and +1.0% on DomainNet over competitive existing methods.</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

Collaborative pseudo-label transfer for few-shot unsupervised domain adaptation

  • 期刊论文

  • 发表日期：

    2025年11月17日

查看全文
  • Song Shi,
  • Jinfang Jia,
  • Wandong Xue,
  • Jianqiang Huang

摘要

In real-world scenarios, few-shot unsupervised domain adaptation (FUDA) faces the dual challenges of limited source supervision and poor target generalization due to the extremely scarce annotated source samples. Existing methods often overlook the restricted learning capacity caused by sparse source labels or fail to effectively utilize the structural information within the target domain to enhance discriminative performance. To address these issues, we propose a novel method, Collaborative Pseudo-label Transfer (CPLT), which jointly improves cross-domain adaptation under few-shot UDA settings. CPLT comprises two key components: a Pseudo-label Guided Source Augmentation (PGSA) mechanism that iteratively selects high-confidence target samples to augment the source domain and strengthen initial representation learning, and a Target-aware Discriminative Modeling (TADM) that leverages pseudo-labeled target data to construct auxiliary classifiers for enhanced inter-class discrimination and reduced misclassification under domain shift. Experiments on three widely used FUDA benchmarks validate the superior performance of CPLT, achieving average accuracy gains of +3.5% on Office-31, +1.4% on Office-Home, and +1.0% on DomainNet over competitive existing methods.