面向鲁棒少样本分类的图注意力原型网络
Graph Attention Prototypical Network for Robust Few-Shot Classification
把原型网络的原型构造换成「伪标签引导的图构造 + 边感知图注意力 + 自适应噪声抑制原型生成器」，这套模块可直接迁移到任何需要从带噪支持集聚合类原型的视觉任务（如带噪少样本检测、开放词表分类的原型校准）。
原文依据 an adaptive noise-robust prototype generator is introduced to dynamically suppress the contributions of noisy samples
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已受到广泛关注，基于度量的方法（如原型网络）建立了强有力的基线。这类方法从支持样本中构造类原型，并通过距离度量对查询样本进行分类，但其性能对标签噪声高度敏感。为应对这一挑战，我们提出了一种新的图注意力原型网络（GAPNet），用于鲁棒的少样本分类。GAPNet 首先分别通过经典 CNN 骨干网络和分组注意力宽度学习模块提取局部特征与全局特征。为减轻标签噪声的影响，我们通过伪标签引导的图构造器显式建模支持样本与查询样本之间的类内与类间关系，随后由边感知图注意力模块处理以捕获拓扑相关性。此外，我们引入了自适应噪声鲁棒原型生成器，动态抑制噪声样本的贡献，从而大幅提升类原型的可靠性。大量实验证明了 GAPNet 对标签噪声的有效性与鲁棒性。与最优方法相比，GAPNet 在三个通用图像基准和一个细粒度分类数据集上于 5-way 5-shot 设置下将准确率提升了 3% ~ 8%。
英文原文摘要 1325 字符
Few-shot learning has attracted extensive attention, with metric-based approaches such as Prototypical Networks establishing strong baselines. These methods construct class prototypes from support samples and classify query samples via distance metrics, but their performance is highly sensitive to label noise. To tackle this challenge, we propose a novel Graph Attention Prototypical Network (GAPNet) for robust few-shot classification. GAPNet first extracts local and global features via a classic CNN backbone and a group attention broad learning module, respectively. To mitigate the impact of label noise, the intra-class and inter-class relationships between support and query samples are explicitly modeled via a pseudo-label guided graph constructor, and then processed by an edge-aware graph attention module to capture topological correlations. Furthermore, an adaptive noise-robust prototype generator is introduced to dynamically suppress the contributions of noisy samples, substantially improving the reliability of class prototypes. Extensive experiments demonstrate the effectiveness and robustness of GAPNet to label noise. Compared to state-of-the-art approaches, GAPNet improves accuracy in the 5-way 5-shot setting by 3% ~ 8% on three general image benchmarks and one fine-grained classification dataset.