Scholarlink

<p>Cross-domain few-shot learning focuses on transferring knowledge from a source domain to an unseen target domain, but traditional methods often rely on simple additive perturbations, which limit their effectiveness in handling domain shifts. To address this limitation, we propose an innovative meta-learning framework augmented by uncertainty generation. Our approach introduces a novel gradient-based uncertainty generation method that treats feature statistics, such as mean and variance, as probabilistic representations assuming an unknown distribution. These statistics are manipulated through task gradients, which allow the model to capture the range of possible variations, thereby generating uncertainty feature distributions that simulate domain biases. Additionally, we incorporate a causal invariant information (CII) module to extract causal features and improve the consistency of task gradients across domains. This module ensures that the task gradients reflect domain-invariant features, reducing the impact of domain-specific noise and providing a more reliable framework for constructing uncertainty boundaries. Together, these components enable the development of an asymptotic meta-learning optimization algorithm that learns generalized knowledge from uncertainty features while optimizing the uncertainty distribution boundaries. Experimental results across nine datasets demonstrate that our method improves the current state-of-the-art by an average of 3.11%, with key innovations in using probabilistic feature statistics, gradient-based uncertainty modeling, and causal feature extraction that enhance cross-domain knowledge transfer more effectively than existing techniques.</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

Uncertainty Generation Meta-training for Cross-domain Few-shot Learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月4日

查看全文
  • Keyang Cheng,
  • Yuze Sun,
  • Yue Yu,
  • Zhe Wang,
  • Hao Wan,
  • Changsheng Peng

摘要

Cross-domain few-shot learning focuses on transferring knowledge from a source domain to an unseen target domain, but traditional methods often rely on simple additive perturbations, which limit their effectiveness in handling domain shifts. To address this limitation, we propose an innovative meta-learning framework augmented by uncertainty generation. Our approach introduces a novel gradient-based uncertainty generation method that treats feature statistics, such as mean and variance, as probabilistic representations assuming an unknown distribution. These statistics are manipulated through task gradients, which allow the model to capture the range of possible variations, thereby generating uncertainty feature distributions that simulate domain biases. Additionally, we incorporate a causal invariant information (CII) module to extract causal features and improve the consistency of task gradients across domains. This module ensures that the task gradients reflect domain-invariant features, reducing the impact of domain-specific noise and providing a more reliable framework for constructing uncertainty boundaries. Together, these components enable the development of an asymptotic meta-learning optimization algorithm that learns generalized knowledge from uncertainty features while optimizing the uncertainty distribution boundaries. Experimental results across nine datasets demonstrate that our method improves the current state-of-the-art by an average of 3.11%, with key innovations in using probabilistic feature statistics, gradient-based uncertainty modeling, and causal feature extraction that enhance cross-domain knowledge transfer more effectively than existing techniques.