DDSF：基于解耦子空间与行列式点过程的鲁棒少样本学习
DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process
用行列式点过程（DPP）的体量最大化来筛选样本、引导扩散增强并构造解耦子空间，可作为提升原型类方法在噪声与难正样本下稳定性的通用插件。
原文依据 employing it to estimate sample confidence to filter anomalous samples from the initial set
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于均值的原型方法在少样本学习中的性能常因噪声与难正样本而受损，其中纠缠的特征表示会导致原型不稳定。本文提出一种基于行列式点过程（DPP）理论的新型“过滤-修复-扩展”框架。该方法以 DPP 为核心逻辑，利用其估计样本置信度以从初始集合中过滤异常样本，通过体量最大化引导扩散过程以增强样本表示，随后最大化协同解耦子空间的体量，从而构建鲁棒且多样的原型子空间。实验结果表明，该方法在多个基准上取得新的最优性能，在少样本学习鲁棒性上取得显著提升。代码见 https://github.com/24sleeping90/DDSF。
英文原文摘要 867 字符
The performance of mean-based prototypical methods in few-shot learning is frequently compromised by noise and hard positives, where entangled feature representations cause prototype instability. We present a novel "Filter-Repair-Expand" framework grounded in Determinantal Point Process (DPP) theory. The method leverages DPP as its core logic, employing it to estimate sample confidence to filter anomalous samples from the initial set, guide a diffusion process via volume-maximization to enhance the sample representation, and subsequently maximize the volume of synergistic disentangled subspaces, constructing robust and diverse prototype subspaces. Experimental results establish new state-of-the-art performance on multiple benchmarks, demonstrating significant gains in few-shot learning robustness. Code is available at https://github.com/24sleeping90/DDSF.