通过双向多视图提示词对齐实现噪声感知少样本学习
Noise-Aware Few-Shot Learning through Bi-directional Multi-View Prompt Alignment
把提示词微调从全局图文匹配推进到区域级 patch-to-prompt 对齐，并用非平衡最优传输抑制不可靠区域，为视觉语言模型在噪声监督下的少样本适配提供了可复用的对齐与样本筛选机制。
原文依据 multi-view prompts combined with unbalanced optimal transport to achieve fine-grained patch-to-prompt correspondence
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉语言模型通过提示词微调具备强大的少样本能力，但仍易受噪声标签影响，噪声会污染提示词并削弱跨模态对齐。现有方法之所以难以应对，是因为它们往往缺乏对细粒度语义线索建模的能力，也无法自适应地区分干净信号与噪声信号。为应对这些挑战，我们提出 NA-MVP，一个通过双向多视图提示词对齐实现噪声感知少样本学习的框架。NA-MVP 建立在一个关键的概念转变之上：鲁棒的提示词学习需要从全局匹配转向区域感知对齐，从而显式区分干净线索与噪声线索。为实现这一点，NA-MVP 采用：(1) 多视图提示词结合非平衡最优传输，在抑制不可靠区域的同时实现细粒度的图像块到提示词对应；(2) 双向提示词设计，捕获互补的面向干净信号与噪声感知的线索，使模型能够聚焦于稳定的语义；(3) 对齐引导的选择性精修策略，利用最优传输仅纠正被错误标注的样本，同时保留可靠数据。在合成与真实噪声基准上的实验表明，NA-MVP 持续优于最优基线，验证了其在噪声监督下实现鲁棒少样本学习的有效性。
英文原文摘要 1383 字符
Vision-language models offer strong few-shot capability through prompt tuning but remain vulnerable to noisy labels, which can corrupt prompts and degrade cross-modal alignment. Existing approaches struggle because they often lack the ability to model fine-grained semantic cues and to adaptively separate clean from noisy signals. To address these challenges, we propose NA-MVP, a framework for Noise-Aware few-shot learning through bi-directional Multi-View Prompt alignment. NA-MVP is built upon a key conceptual shift: robust prompt learning requires moving from global matching to region-aware alignment that explicitly distinguishes clean cues from noisy ones. To realize this, NA-MVP employs (1) multi-view prompts combined with unbalanced optimal transport to achieve fine-grained patch-to-prompt correspondence while suppressing unreliable regions; (2) a bi-directional prompt design that captures complementary clean-oriented and noise-aware cues, enabling the model to focus on stable semantics; and (3) an alignment-guided selective refinement strategy that uses optimal transport to correct only mislabeled samples while retaining reliable data. Experiments on synthetic and real-world noisy benchmarks demonstrate that NA-MVP consistently outperforms state-of-the-art baselines, confirming its effectiveness in enabling robust few-shot learning under noisy supervision.