数据中心元学习实现鲁棒少样本泛化
Data-Centric Meta-Learning for Robust Few-Shot Generalization
提出一种在元训练阶段就引入可学习视觉提示词来对齐任务输入分布、缓解梯度冲突的元学习框架，为视觉少样本跨域泛化提供了一种数据中心的训练策略，且测试时仅更新轻量提示词和分类器，骨干网络冻结，便于在视觉任务中复用。
原文依据 DCML accomplishes this alignment through a meta-learnable visual prompt that is integrated into the entire meta-learning process
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论少样本学习旨在利用有限数据快速适应未见任务。基于优化的元学习通过从多样任务中获取共享先验知识来应对这一挑战。然而，在未见任务与训练任务差异显著的跨域场景中，其有效性会下降。我们将这种性能下降归因于未能获取可泛化的先验知识，其根本原因在于梯度差异——在具有多样任务分布的元训练环境中出现的冲突更新方向。为实现鲁棒的少样本泛化，我们提出了数据中心元学习（DCML），这是一个通过将任务特定的输入分布与共享先验知识对齐来缓解梯度差异的新框架。DCML通过一个可元学习的视觉提示词来实现这种对齐，该提示词被集成到整个元学习过程中——不同于先前仅局限于测试时自适应的基于提示词的方法。在元训练期间，该提示词转换每个任务的输入以诱导更一致的梯度，从而促进可泛化先验知识的学习。利用这种鲁棒的知识，DCML通过仅更新轻量级提示词和分类器而保持骨干网络冻结，实现了快速且参数高效的测试时自适应。大量实验表明，DCML始终优于基线，尤其是在具有挑战性的少样本跨域场景中，为鲁棒的元学习确立了数据中心的视角。
英文原文摘要 1561 字符
Few-shot learning aims to enable rapid adaptation to unseen tasks using limited data. Optimization-based meta-learning addresses this challenge by acquiring shared prior knowledge across diverse tasks. However, its effectiveness degrades in cross-domain scenarios where unseen tasks differ significantly from training tasks. We identify this degradation as a failure to acquire generalizable prior knowledge, which is fundamentally caused by gradient discrepancies--conflicting update directions arising in the meta-training environment with diverse task distributions. To achieve robust few-shot generalization, we propose Data-Centric Meta-Learning (DCML), a novel framework that mitigates gradient discrepancies by aligning task-specific input distributions with shared prior knowledge. DCML accomplishes this alignment through a meta-learnable visual prompt that is integrated into the entire meta-learning process--unlike previous prompt-based methods restricted solely to test-time adaptation. During meta-training, the prompt transforms each task's inputs to induce more consistent gradients, thereby facilitating the learning of generalizable prior knowledge. Leveraging this robust knowledge, DCML enables rapid and parameter-efficient test-time adaptation by updating only the lightweight prompt and classifier while keeping the backbone frozen.Extensive experiments demonstrate that DCML consistently outperforms baselines, particularly in challenging few-shot cross-domain scenarios, establishing a data-centric perspective for robust meta-learning.